© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9464
    Prev
    Next
    INDEX
    Explanations

    DNS, domain names, and internet infrastructure

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on numeric/semi‐numeric tokens conveying site statistics or technical metrics (e.g. visitor counts, IP addresses, server and directory values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical website metadata and statistics, particularly information about web servers, hosting, and site analytics.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    descriptions of website analytics and hosting details, such as traffic/SEO metrics, server/IP/DNS information, and site valuation stats.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ре
    0.72
    को
    0.69
    становка
    0.68
    हत्या
    0.68
    декс
    0.68
    сти
    0.66
    ता
    0.65
    стави
    0.65
    че
    0.65
    ologues
    0.64
    POSITIVE LOGITS
     Airtel
    0.75
     Meskipun
    0.74
     Pupp
    0.70
     Targeting
    0.70
     SSL
    0.68
     HIS
    0.68
     Chaque
    0.68
     Several
    0.68
     Vodafone
    0.68
     Seems
    0.67
    Activations Density 0.010%

    No Known Activations