© 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. 9629
    Prev
    Next
    INDEX
    Explanations

    quoted titles

    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
     essentiels
    -2.16
    ㋛
    -2.13
     menyen
    -2.09
    ’
    -2.08
    圌
    -2.02
    饜
    -2.02
     tâ
    -1.96
     visse
    -1.92
    ;-
    -1.91
    ఽ
    -1.88
    POSITIVE LOGITS
     by
    2.20
     Our
    1.94
     through
    1.80
     because
    1.80
     as
    1.66
     worin
    1.65
     Not
    1.64
     is
    1.63
     nuestra
    1.62
     There
    1.61
    Activations Density 0.059%

    No Known Activations