© 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. 41540
    Prev
    Next
    INDEX
    Explanations

    how to

    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
    蠵
    -1.49
    暑い
    -1.45
     všetkých
    -1.44
    %).
    -1.43
    まだまだ
    -1.42
    そろそろ
    -1.41
     rencontre
    -1.40
    cinoma
    -1.38
    …」
    -1.34
     menunjukkan
    -1.34
    POSITIVE LOGITS
    ?
    1.72
    [
    1.70
    {
    1.48
     avevano
    1.42
    (
    1.41
     HISTORY
    1.39
    したが
    1.39
    ),
    1.34
     without
    1.31
     lakini
    1.28
    Activations Density 0.080%

    No Known Activations