© 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. 68322
    Prev
    Next
    INDEX
    Explanations

    facial expressions and emotion

    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
    >
    -1.41
    玙
    -1.35
    ként
    -1.35
    ён
    -1.27
    .}(
    -1.25
     promu
    -1.24
    s
    -1.21
    ому
    -1.20
    龊
    -1.20
     esquerdo
    -1.19
    POSITIVE LOGITS
     ansik
    1.53
     deterioro
    1.44
     thofe
    1.36
     velikost
    1.35
    uminense
    1.31
    再び
    1.30
     different
    1.30
    今度は
    1.30
    But
    1.29
    どうか
    1.29
    Activations Density 0.008%

    No Known Activations