© 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. 68382
    Prev
    Next
    INDEX
    Explanations

    switch statement

    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
    o
    -1.70
     methode
    -1.60
     această
    -1.56
     decât
    -1.56
     fiecare
    -1.55
     was
    -1.52
     nivå
    -1.52
     laatste
    -1.50
     când
    -1.48
    が多く
    -1.48
    POSITIVE LOGITS
     them
    1.96
     mereka
    1.95
    </b>
    1.91
    توضیحات
    1.63
     они
    1.61
    })()
    1.61
     contexto
    1.57
    1.57
     cómo
    1.55
     including
    1.55
    Activations Density 0.009%

    No Known Activations