© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1561
    Prev
    Next
    INDEX
    Explanations

    connect, geo, take, United

    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
    ('.');
    -0.92
    (',');
    -0.90
     OBITUARY
    -0.83
     questioned
    -0.82
    inderung
    -0.78
    arius
    -0.77
    ('/');
    -0.77
    INTAGE
    -0.77
    комплект
    -0.76
    stacks
    -0.75
    POSITIVE LOGITS
    iowa
    0.85
    邯
    0.85
    íaco
    0.80
     нужен
    0.79
    どんな
    0.77
    ounid
    0.77
    僕
    0.77
    })(
    0.76
     exception
    0.76
     null
    0.75
    Activations Density 0.003%

    No Known Activations