© 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. 10-GEMMASCOPE-RES-131K
    7. 60461
    Prev
    Next
    INDEX
    Explanations

    Erin Peace

    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_10/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
    '
    -2.27
    」、「
    -1.92
     amusing
    -1.90
    ar
    -1.71
     envio
    -1.66
    瀟
    -1.61
    hebung
    -1.60
    諴
    -1.60
    صدر
    -1.59
     occasional
    -1.56
    POSITIVE LOGITS
    <i>
    2.34
    </h1>
    2.19
    </b>
    1.98
    หรือ
    1.90
    WithEmail
    1.77
     ہے۔
    1.66
     praticamente
    1.66
    )}\
    1.64
    ).
    1.63
     inesper
    1.62
    Activations Density 0.008%

    No Known Activations