© 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. 64120
    Prev
    Next
    INDEX
    Explanations

    bags, pouches, and luggage

    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_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
    cepan
    -0.88
    wkt
    -0.75
     nutrient
    -0.75
     stockings
    -0.75
    ندي
    -0.74
    emplacement
    -0.73
    财产
    -0.73
     shrou
    -0.72
     cupboard
    -0.71
     manifiesta
    -0.70
    POSITIVE LOGITS
     gus
    0.93
    華
    0.83
    gus
    0.83
     zie
    0.82
     crossbody
    0.81
     STUDIES
    0.80
     oktober
    0.79
    マチ
    0.79
     magnetic
    0.79
    innig
    0.79
    Activations Density 0.018%

    No Known Activations