© 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. 21253
    Prev
    Next
    INDEX
    Explanations

    mentions of Alice

    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
     is
    -3.36
    ’
    -2.84
    on
    -2.67
    >
    -2.63
    <em>
    -2.53
    ad
    -2.45
    t
    -2.44
    il
    -2.44
    E
    -2.34
     they
    -2.31
    POSITIVE LOGITS
    鉨
    3.38
    쨩
    3.08
    噲
    2.97
    ⌵
    2.81
    linawan
    2.67
    IZACIÓN
    2.66
    샅
    2.63
    蕻
    2.55
    iſter
    2.52
     coun
    2.45
    Activations Density 0.005%

    No Known Activations