© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12089
    Prev
    Next
    INDEX
    Explanations

    creation and update timestamps

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

    The neuron activates on metadata labels indicating publication or update information (e.g. “Published,” “updated by,” etc.).

    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_31_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
     είχε
    0.77
     чого
    0.75
    赭
    0.74
     jeopard
    0.73
     devoid
    0.71
    ഷ്ട്ര
    0.70
     cherished
    0.69
     जुड़ा
    0.68
     ಏನ
    0.68
    kého
    0.68
    POSITIVE LOGITS
     by
    1.18
     on
    1.02
    by
    0.93
    at
    0.88
     at
    0.86
     in
    0.79
    byId
    0.77
    于
    0.76
     توسط
    0.75
    in
    0.75
    Activations Density 0.091%

    No Known Activations