© 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. 39755
    Prev
    Next
    INDEX
    Explanations

    code delimiters, brackets, and code constructs

    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
     After
    -2.14
    忖
    -2.11
    ’
    -2.03
     mereka
    -2.00
    珖
    -1.98
     Although
    -1.97
    下方
    -1.95
     usually
    -1.91
    ⽌
    -1.90
     estuviera
    -1.87
    POSITIVE LOGITS
     the
    2.64
     Ebenen
    2.38
     leeren
    2.38
    媃
    2.34
    寕
    2.31
     Hinblick
    2.28
     hordes
    2.28
    褙
    2.23
    好吃的
    2.22
    釤
    2.19
    Activations Density 0.001%

    No Known Activations