© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8694
    Prev
    Next
    INDEX
    Explanations

    business books and authors

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

    The neuron fires on the numeric metadata (years, volume and page numbers, etc.) that appear in academic‐style reference entries.

    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
    -
    1.11
    ,
    1.08
     
    1.05
     in
    0.99
     at
    0.96
     that
    0.94
     as
    0.91
    /
    0.91
     to
    0.87
     and
    0.87
    POSITIVE LOGITS
    льнявыя
    1.00
     romanzo
    0.96
    <unused1004>
    0.96
    <unused1006>
    0.93
    <unused404>
    0.93
    磵
    0.91
    picode
    0.91
    <unused1056>
    0.91
    <unused1130>
    0.90
    <unused1086>
    0.89
    Activations Density 0.021%

    No Known Activations