© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59471
    Prev
    Next
    INDEX
    Explanations

    abbreviations for varieties or species

    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
     when
    -2.03
     just
    -1.91
     because
    -1.66
     time
    -1.61
     if
    -1.55
    ↵
    -1.55
     ketika
    -1.54
    when
    -1.50
     where
    -1.50
     as
    -1.50
    POSITIVE LOGITS
     delightfully
    1.63
     např
    1.63
     unbelievably
    1.59
    '
    1.57
     Président
    1.56
    Wm
    1.55
    有些不
    1.54
    罍
    1.54
     pourront
    1.54
     frança
    1.54
    Activations Density 0.126%

    No Known Activations