© 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. 15602
    Prev
    Next
    INDEX
    Explanations

    elected from region

    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
    <bos>
    -1.63
    StoryboardSegue
    -1.38
    让他
    -1.34
    ﻷ
    -1.34
    咈
    -1.30
    ,”
    -1.30
    },"
    -1.29
    他说
    -1.27
    ที่
    -1.25
     nawet
    -1.25
    POSITIVE LOGITS
     of
    1.41
    Icy
    1.33
    chanel
    1.30
     speelt
    1.30
    Requiem
    1.28
     Many
    1.27
    óstico
    1.25
     avendo
    1.24
    oscar
    1.23
    Pulp
    1.23
    Activations Density 0.063%

    No Known Activations