© 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. 8985
    Prev
    Next
    INDEX
    Explanations

    password or credential

    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
     these
    -1.90
    </strong>
    -1.77
     variété
    -1.66
     his
    -1.63
     he
    -1.61
     you
    -1.59
    美国的
    -1.50
    (
    -1.49
     mostra
    -1.48
    鹮
    -1.48
    POSITIVE LOGITS
     formidable
    1.42
     jub
    1.41
     jagged
    1.36
     tendremos
    1.34
    .
    1.31
    鹦
    1.31
     Fundament
    1.30
     dejando
    1.30
    ină
    1.27
     Они
    1.25
    Activations Density 0.015%

    No Known Activations