© 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. 15031
    Prev
    Next
    INDEX
    Explanations

    listing items

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

    The neuron fires on the token “list” (in any casing or as part of identifiers), signaling occurrences of the word “list” (e.g. list commands, methods, or class names).

    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
     {
    -1.70
    }
    -1.58
    $
    -1.55
    秾
    -1.52
     He
    -1.52
    那就
    -1.47
    >
    -1.45
    沵
    -1.41
    吱
    -1.41
    lnie
    -1.40
    POSITIVE LOGITS
     from
    1.98
     for
    1.75
     through
    1.62
     at
    1.62
     out
    1.55
    '
    1.52
     naše
    1.49
     sensação
    1.45
     verdieping
    1.45
     before
    1.41
    Activations Density 0.046%

    No Known Activations