© 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. 2999
    Prev
    Next
    INDEX
    Explanations

    conversational or structured text

    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
    💛
    -0.74
    urity
    -0.74
    アリ
    -0.71
    IEDAD
    -0.70
    ✨✨
    -0.69
     realidad
    -0.68
    ♡♡
    -0.68
    💞
    -0.68
     什么
    -0.67
    serializer
    -0.67
    POSITIVE LOGITS
     ChatGPT
    0.98
    ⾏
    0.94
     FTX
    0.89
    ękuję
    0.87
    ratory
    0.86
     "}";
    0.82
     peor
    0.81
    órios
    0.78
    bạn
    0.76
    Digite
    0.75
    Activations Density 0.000%

    No Known Activations