© 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. 48579
    Prev
    Next
    INDEX
    Explanations

    face or face-saving

    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
    IVIDUAL
    -0.75
    Aladdin
    -0.73
     Kis
    -0.72
    дь
    -0.70
    poca
    -0.70
    vois
    -0.69
    的生活
    -0.69
    ウンサー
    -0.68
     Gland
    -0.68
     Gyne
    -0.68
    POSITIVE LOGITS
     face
    2.89
    face
    2.20
    Face
    1.91
     Face
    1.91
    FACE
    1.74
     FACE
    1.63
     save
    1.59
    面子
    1.59
     faces
    1.56
     saving
    1.44
    Activations Density 0.010%

    No Known Activations