© 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. 38766
    Prev
    Next
    INDEX
    Explanations

    names after semicolon

    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
    N
    -2.03
     jego
    -1.74
    鲀
    -1.73
     يونيو
    -1.70
     что
    -1.69
    除去
    -1.65
    лива
    -1.57
     فبراير
    -1.57
    ため
    -1.55
    铍
    -1.55
    POSITIVE LOGITS
    ’
    1.80
    附近的
    1.78
    젊
    1.73
     schuldig
    1.71
     MANY
    1.65
     bedenken
    1.64
     étage
    1.63
     On
    1.63
     a
    1.63
     мелки
    1.62
    Activations Density 0.082%

    No Known Activations