© 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. 10-GEMMASCOPE-RES-131K
    7. 22023
    Prev
    Next
    INDEX
    Explanations

    programming, science, and specific entities

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

    This neuron responds to programming API and class names (e.g., camel-cased technical identifiers like NSCoder or CodeAnalysis).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     
    -1.95
     "
    -1.82
    ↵
    -1.79
    AM
    -1.77
    ER
    -1.70
    AT
    -1.69
    TacToe
    -1.66
    AN
    -1.60
     aliment
    -1.59
    をもら
    -1.59
    POSITIVE LOGITS
    al
    2.44
    istocene
    2.31
    ?”
    2.28
    to
    2.22
    where
    2.13
    轳
    2.08
    <bos>
    2.03
    in
    2.02
     ();
    1.90
    ("")){
    1.90
    Activations Density 0.000%

    No Known Activations