© 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. 68920
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    tuigen
    -1.65
    )("
    -1.55
    $),
    -1.52
    २
    -1.52
    \%)
    -1.52
    雳
    -1.51
    +)/
    -1.51
    相続
    -1.48
    ۴
    -1.48
     catég
    -1.47
    POSITIVE LOGITS
     is
    1.70
     in
    1.67
     größe
    1.44
    .
    1.38
     a
    1.36
     când
    1.33
     sowieso
    1.33
     fomentar
    1.31
    1
    1.30
    hæ
    1.30
    Activations Density 0.066%

    No Known Activations