© 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. 63940
    Prev
    Next
    INDEX
    Explanations

    living people; strict code

    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
     direitos
    -0.72
     برگزار
    -0.71
    idazole
    -0.71
     milhares
    -0.71
    حية
    -0.66
    рации
    -0.66
    גור
    -0.65
    VISIT
    -0.65
     intang
    -0.65
    ベルト
    -0.64
    POSITIVE LOGITS
     os
    0.69
    नो
    0.66
    required
    0.65
     osse
    0.63
    喝
    0.63
    党员
    0.63
     vue
    0.63
    をしました
    0.62
    REQUIRED
    0.62
    की
    0.62
    Activations Density 0.067%

    No Known Activations