© 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. 73328
    Prev
    Next
    INDEX
    Explanations

    lists of

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ↵↵
    -2.05
    .
    -2.03
    O
    -1.86
     .
    -1.74
     {
    -1.73
    fillment
    -1.68
    ulism
    -1.65
    urization
    -1.60
    peteer
    -1.58
    quatch
    -1.53
    POSITIVE LOGITS
     list
    2.52
    list
    2.25
     gruppen
    2.02
    </strong>
    1.96
    '
    1.88
    リスト
    1.85
     newList
    1.85
     список
    1.83
    лении
    1.80
     ledig
    1.76
    Activations Density 0.094%

    No Known Activations