© 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. 59882
    Prev
    Next
    INDEX
    Explanations

    produce or emit something

    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
     have
    -1.50
    tituts
    -1.47
    鳎
    -1.44
    please
    -1.38
    in
    -1.30
    man
    -1.30
    tdessen
    -1.29
    tech
    -1.28
    since
    -1.27
    return
    -1.27
    POSITIVE LOGITS
     özellikle
    1.38
     When
    1.35
     kaikki
    1.31
    Ꮞ
    1.28
    zdroj
    1.27
     unſ
    1.27
     doğum
    1.24
     pernyataan
    1.23
     wiederhol
    1.23
    When
    1.20
    Activations Density 0.110%

    No Known Activations