© 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. 57519
    Prev
    Next
    INDEX
    Explanations

    code and technical context keywords

    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
     wären
    -0.92
    Also
    -0.87
     --;
    -0.85
     šte
    -0.83
    ivez
    -0.83
    Scene
    -0.83
    úrate
    -0.80
    --]
    -0.79
     vanwege
    -0.77
     kõik
    -0.77
    POSITIVE LOGITS
     مشار
    0.82
    lottery
    0.79
    defaultProps
    0.77
    рам
    0.77
    connectivity
    0.76
     Regula
    0.75
     blocks
    0.74
    Hoog
    0.74
    忾
    0.73
    积累
    0.72
    Activations Density 0.001%

    No Known Activations