© 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. 21322
    Prev
    Next
    INDEX
    Explanations

    PEM, pem, bed, sam, vcf filenames

    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
    -1.86
    ?’
    -1.66
    Koordinaten
    -1.56
    …)
    -1.55
     расходы
    -1.55
    name
    -1.54
    h
    -1.53
    re
    -1.48
    r
    -1.46
    %;
    -1.43
    POSITIVE LOGITS
    灕
    1.75
     uniquement
    1.66
     eğiti
    1.50
     démocr
    1.37
     Entdecken
    1.35
     musíte
    1.34
    ära
    1.33
     vulgaires
    1.33
    demás
    1.31
    驯
    1.31
    Activations Density 0.003%

    No Known Activations