© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68799
    Prev
    Next
    INDEX
    Explanations

    pathseach otherkulinereacheach othereacheach othereachpathseach othereacheach other

    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_22/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
     colchón
    -0.82
    ibrated
    -0.81
     fin
    -0.77
    癣
    -0.77
    ĭ
    -0.74
     Yeats
    -0.74
     Gerät
    -0.73
    KommentareTeilen
    -0.73
     Canucks
    -0.72
    ulated
    -0.72
    POSITIVE LOGITS
     each
    0.83
    紝
    0.73
    büro
    0.73
    𝖓
    0.72
     muun
    0.72
     kuliner
    0.71
     рынка
    0.70
     Moraes
    0.69
    άζ
    0.69
    enoid
    0.69
    Activations Density 0.227%

    No Known Activations