© 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. 15535
    Prev
    Next
    INDEX
    Explanations

    programming languages and personalities

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

    The neuron is looking for named entities—proper nouns like place names, organizations, people, etc.

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

    proper nouns, especially place names and geographic locations.

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

    proper nouns, especially named entities like places, organizations, brands, and personal or product names.

    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
    Oregon
    0.89
     系统
    0.86
     Oregon
    0.82
    他们
    0.79
     ரயில்
    0.75
    那些
    0.75
     Hadoop
    0.75
    renewcommand
    0.73
    وسی
    0.73
     TNF
    0.71
    POSITIVE LOGITS
    flutter
    1.02
     Flutter
    0.90
     Anambra
    0.87
    Flutter
    0.83
     caribbean
    0.80
     venezol
    0.76
     dimiliki
    0.76
     flutter
    0.75
     facie
    0.75
     mozz
    0.74
    Activations Density 3.957%

    No Known Activations