© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15709
    Prev
    Next
    INDEX
    Explanations

    comment markers or question prefixes

    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
    Negative Logits
    .'-
    -2.19
    ❣️
    -1.81
    🍷
    -1.77
    .-"
    -1.66
    😋
    -1.64
    🙏🙏
    -1.63
    💐
    -1.63
    😬
    -1.60
    🙃
    -1.60
    tiendo
    -1.59
    POSITIVE LOGITS
    0
    1.93
     didn
    1.61
     will
    1.59
    5
    1.57
    *
    1.57
    ?
    1.55
     –
    1.50
    4
    1.46
     схе
    1.45
    一时间
    1.43
    Activations Density 0.000%

    No Known Activations