© 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. 93506
    Prev
    Next
    INDEX
    Explanations

    examples in code and 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
    sy
    -0.66
    Hij
    -0.66
    Rey
    -0.65
     bleus
    -0.63
    Carte
    -0.63
    cardia
    -0.63
    ிர
    -0.62
     הז
    -0.62
     CGFloat
    -0.61
    Saj
    -0.61
    POSITIVE LOGITS
    mlx
    0.77
    商店
    0.77
    FUNCTION
    0.69
    říklad
    0.67
    фильм
    0.66
    店舗
    0.66
     retail
    0.65
    refine
    0.65
    Sleep
    0.65
    Premios
    0.64
    Activations Density 0.098%

    No Known Activations