© 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. 45050
    Prev
    Next
    INDEX
    Explanations

    deception and fooling

    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
    𓐍
    -1.87
    
    -1.73
     nouve
    -1.64
    '?
    -1.59
     LEYENDO
    -1.58
    鈊
    -1.57
    پان
    -1.54
     میتوان
    -1.54
     hade
    -1.50
    Ꭸ
    -1.50
    POSITIVE LOGITS
    {
    2.08
    ;
    1.84
    *
    1.80
    <
    1.78
    ",
    1.77
    .
    1.69
    wickshire
    1.62
    }
    1.55
    ття
    1.53
    $,
    1.52
    Activations Density 0.009%

    No Known Activations