© 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. 65551
    Prev
    Next
    INDEX
    Explanations

    I followed by interface/initializer

    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
     wund
    -0.94
     Verf
    -0.94
    遇到
    -0.93
     Someone
    -0.90
    칭
    -0.85
    impossible
    -0.85
    ”;
    -0.85
    ;
    -0.85
     کسی
    -0.85
    IBOutlet
    -0.84
    POSITIVE LOGITS
    τών
    0.99
    uyasha
    0.91
     tillgäng
    0.90
    typal
    0.90
    }(-
    0.88
    商店
    0.86
    alisis
    0.85
     samti
    0.83
     atrak
    0.83
     Россию
    0.83
    Activations Density 0.001%

    No Known Activations