© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6897
    Prev
    Next
    INDEX
    Explanations

    redevelopment, redeem, bereavement

    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
    Negative Logits
    ].
    -3.45
    </em>
    -3.06
    `
    -3.06
    \
    -3.06
    2
    -3.06
    1
    -2.75
    }{
    -2.58
    m
    -2.55
    }
    -2.53
    \_
    -2.48
    POSITIVE LOGITS
    毉
    2.88
    咵
    2.86
     باسلام
    2.84
     escuchadas
    2.73
     онъ
    2.72
     花纹
    2.72
    蹓
    2.72
     itſelf
    2.63
     consideradas
    2.58
    ㈬
    2.50
    Activations Density 0.003%

    No Known Activations