© 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. 112064
    Prev
    Next
    INDEX
    Explanations

    state of the art

    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
     to
    -2.00
     It
    -1.96
     Should
    -1.63
     AFTER
    -1.53
     I
    -1.50
     มัน
    -1.50
     และ
    -1.49
     sostu
    -1.48
     flera
    -1.38
     många
    -1.37
    POSITIVE LOGITS
    别人的
    1.73
    '
    1.55
    :"
    1.50
    if
    1.50
    鬭
    1.46
     sumber
    1.44
     JEAN
    1.41
     HENRY
    1.39
     BECK
    1.37
     cuit
    1.37
    Activations Density 0.043%

    No Known Activations