© 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. 10286
    Prev
    Next
    INDEX
    Explanations

    code blocks and file structures

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

    This neuron identifies parenthetical asides or editorial remarks (e.g. anything set off by parentheses or labeled “Editor’s note”/“Disclosure”).

    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
     матри
    0.66
     항상
    0.62
    
    0.62
    ()">
    0.60
     finalList
    0.60
     TRANSPORTURI
    0.60
    ->"
    0.59
     کوډ
    0.59
     домаћинстава
    0.59
    toList
    0.58
    POSITIVE LOGITS
    ▲
    0.75
    Jakarta
    0.61
    كتب
    0.60
    Đáp
    0.60
    Bước
    0.60
    **
    0.58
    Trong
    0.57
    <em>
    0.57
    КИ
    0.55
    Το
    0.55
    Activations Density 0.020%

    No Known Activations