© 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. 45345
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or variables

    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
     segítség
    -1.42
     a
    -1.38
    ҫ
    -1.34
    </strong>
    -1.31
    éviter
    -1.25
     verseny
    -1.17
    Toeschouwers
    -1.16
     Tatsache
    -1.16
    </b>
    -1.14
     souvent
    -1.14
    POSITIVE LOGITS
     now
    1.47
    .
    1.39
    nå
    1.26
     that
    1.24
     still
    1.20
    vieux
    1.20
    ریزی
    1.20
     but
    1.16
    經歷
    1.15
    řel
    1.13
    Activations Density 0.002%

    No Known Activations