© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116243
    Prev
    Next
    INDEX
    Explanations

    * then number

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

    This neuron fires on the “d” in abbreviated West‐reporter citations (e.g. “F.2d,” “So.2d,” “F. Supp.,” etc.), i.e. it detects court‐reporter volume designators.

    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
     Escrow
    -0.80
    σμο
    -0.80
    ENES
    -0.75
    %%%%%%
    -0.74
     bombar
    -0.73
    мә
    -0.73
    keydown
    -0.71
    LEI
    -0.71
    ストン
    -0.71
    никюр
    -0.70
    POSITIVE LOGITS
     columns
    3.78
     column
    3.45
    columns
    3.08
    column
    2.97
     Columns
    2.80
     Column
    2.77
    Column
    2.75
    Columns
    2.61
     columnas
    2.55
     colonnes
    2.27
    Activations Density 0.061%

    No Known Activations