© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66397
    Prev
    Next
    INDEX
    Explanations

    street, north, good, guide, sight, race, suit, brand, plan, cover, Life

    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
     and
    -2.69
     to
    -2.52
    诹
    -2.28
     Erzä
    -2.28
     หรือ
    -2.25
     in
    -2.25
     který
    -2.20
    のイメージ
    -2.20
    鉛筆
    -2.16
    猛然
    -2.16
    POSITIVE LOGITS
     itſelf
    2.98
    to
    2.95
     rajut
    2.89
    quíni
    2.80
     και
    2.73
    Setiap
    2.67
    what
    2.63
     bekasi
    2.61
    .
    2.58
     kesel
    2.56
    Activations Density 0.077%

    No Known Activations