© 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. 34-GEMMASCOPE-RES-131K
    7. 23858
    Prev
    Next
    INDEX
    Explanations

    summary, strengths, article sections

    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_34/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
    願意
    -1.11
    譴
    -1.06
    '
    -0.99
    Глава
    -0.99
    ット
    -0.97
     may
    -0.96
     greater
    -0.96
    嚮
    -0.96
     to
    -0.95
     at
    -0.95
    POSITIVE LOGITS
     моя
    1.30
    偁
    1.28
     américa
    1.26
    rof
    1.24
     mondi
    1.23
     achet
    1.22
    镲
    1.21
    纐
    1.17
    以上
    1.16
    ©
    1.16
    Activations Density 0.002%

    No Known Activations