© 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. 85526
    Prev
    Next
    INDEX
    Explanations

    patron or patrons

    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
    ть
    -2.55
     they
    -2.50
     Of
    -2.28
    ﻒ
    -2.25
    io
    -2.14
     \_
    -2.14
     evoke
    -2.11
     olympiques
    -2.11
    }=\
    -2.08
    TintMode
    -2.08
    POSITIVE LOGITS
    ྜ
    2.25
    ቍ
    2.02
     Their
    1.98
     シリーズ
    1.98
    o
    1.95
    们的
    1.93
    </td>
    1.91
    インチ
    1.91
     thc
    1.89
     spil
    1.88
    Activations Density 0.002%

    No Known Activations