© 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. 9899
    Prev
    Next
    INDEX
    Explanations

    CSS class names

    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
    已經
    -1.44
     gâ
    -1.40
     DIFFERENT
    -1.39
    GRANT
    -1.34
    ях
    -1.34
     surpren
    -1.32
     Duitse
    -1.31
     inond
    -1.30
    ťaž
    -1.29
     bouteilles
    -1.28
    POSITIVE LOGITS
     when
    2.73
     because
    2.45
     for
    2.28
     we
    2.19
     in
    1.89
     after
    1.88
     on
    1.78
     at
    1.70
     during
    1.66
     although
    1.61
    Activations Density 0.008%

    No Known Activations