© 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. 10-GEMMASCOPE-RES-131K
    7. 71655
    Prev
    Next
    INDEX
    Explanations

    proper nouns and symbols

    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
    艿
    -2.69
     formidable
    -2.67
    jenige
    -2.59
    pendentif
    -2.56
     you
    -2.52
     dijeron
    -2.45
     llegan
    -2.34
    跸
    -2.34
     této
    -2.34
     hinder
    -2.33
    POSITIVE LOGITS
    en
    3.33
    h
    2.95
    er
    2.89
    塤
    2.84
    —
    2.67
    e
    2.61
    ta
    2.45
    </td>
    2.45
    le
    2.44
    r
    2.42
    Activations Density 0.000%

    No Known Activations