© 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. 22-GEMMASCOPE-RES-131K
    7. 33697
    Prev
    Next
    INDEX
    Explanations

    countries and cities

    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
    Comté
    -0.96
    谩
    -0.92
    Durata
    -0.90
    mbolos
    -0.89
     poziom
    -0.88
    ള്
    -0.88
    棂
    -0.88
    
    -0.88
    ép
    -0.86
     attaque
    -0.85
    POSITIVE LOGITS
    文
    0.95
    O
    0.93
    V
    0.91
    ，
    0.90
    OO
    0.90
    OC
    0.88
    新
    0.88
     Suicide
    0.88
    Kanpo
    0.85
    累
    0.85
    Activations Density 0.078%

    No Known Activations