© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77728
    Prev
    Next
    INDEX
    Explanations

    copyright, author, project

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

    The neuron fires on code‐style syntax tokens (e.g. CSS/property names and punctuation in code blocks).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Frente
    -0.73
     привести
    -0.73
     mịn
    -0.71
     valla
    -0.70
    Джере
    -0.70
     表示
    -0.69
    éry
    -0.67
     altro
    -0.67
     kritik
    -0.67
     mitte
    -0.67
    POSITIVE LOGITS
     table
    5.31
     Table
    5.28
    Table
    5.25
    TABLE
    3.92
    table
    3.81
     TABLE
    3.77
     tables
    3.00
    getTable
    3.00
    Таблица
    2.73
    テーブル
    2.72
    Activations Density 0.011%

    No Known Activations