© 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. 889
    Prev
    Next
    INDEX
    Explanations

    draft followed by document types

    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
     -
    -1.88
    跻
    -1.82
    within
    -1.69
                
    -1.64
    rativa
    -1.59
    than
    -1.57
    Ot
    -1.54
    during
    -1.53
    进入了
    -1.52
    WITH
    -1.48
    POSITIVE LOGITS
     of
    2.25
    IZONTAL
    1.78
     also
    1.72
     as
    1.71
    .''
    1.64
    퐹
    1.62
    肪
    1.61
     until
    1.59
     republiky
    1.59
     always
    1.52
    Activations Density 0.021%

    No Known Activations