© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47488
    Prev
    Next
    INDEX
    Explanations

    web api calls

    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
    Rptr
    -1.71
    пите
    -1.66
    vency
    -1.61
    酪
    -1.54
    TokenNameDOT
    -1.54
    ︲
    -1.45
    чої
    -1.43
    InputBorder
    -1.43
    嘻
    -1.43
    LEncoder
    -1.38
    POSITIVE LOGITS
     what
    1.66
    (
    1.43
     this
    1.43
    -
    1.42
     who
    1.41
     how
    1.31
     jemanden
    1.29
     nyingi
    1.23
     heiß
    1.22
    >\<
    1.22
    Activations Density 0.038%

    No Known Activations