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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 16119
    Prev
    Next
    INDEX
    Explanations

    why I can't

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

    The neuron lights up on business-or marketing-style terms—brand names, company/service verbs, and promotional language.

    oai_token-act-pair · o4-miniTriggered 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
    ங்கிணை
    0.39
     гэта
    0.37
     为
    0.36
     ў
    0.35
    illions
    0.35
     از
    0.35
    LLOW
    0.35
    欧洲
    0.35
    Ý
    0.34
    ocolate
    0.34
    POSITIVE LOGITS
    تبقى
    0.36
    বির
    0.36
     mindset
    0.36
     calmness
    0.36
     methodical
    0.35
    AsyncTask
    0.35
    が必要
    0.34
     doPost
    0.34
    льо
    0.34
     selfless
    0.34
    Activations Density 0.605%

    No Known Activations