© 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. 104540
    Prev
    Next
    INDEX
    Explanations

    describing actions and results

    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
     as
    -2.31
     who
    -1.51
    магазин
    -1.38
    devise
    -1.34
    いいのか
    -1.32
    سبب
    -1.30
    راجع
    -1.29
     menerapkan
    -1.29
    Ҭ
    -1.27
     through
    -1.26
    POSITIVE LOGITS
     you
    1.94
    (
    1.62
    \
    1.47
    ke
    1.29
    if
    1.29
    ku
    1.26
    ;
    1.25
     permet
    1.20
    or
    1.20
    [
    1.20
    Activations Density 0.213%

    No Known Activations