© 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. 22-GEMMASCOPE-RES-131K
    7. 71576
    Prev
    Next
    INDEX
    Explanations

    part after noun

    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_22/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
     rése
    -1.75
    ţele
    -1.73
     frequentemente
    -1.71
     pán
    -1.70
     kompati
    -1.66
     garantir
    -1.65
     広場
    -1.64
    歺
    -1.60
     negru
    -1.60
     Très
    -1.59
    POSITIVE LOGITS
     in
    2.02
     on
    1.78
     with
    1.77
     at
    1.66
     three
    1.62
     after
    1.61
     more
    1.58
     creating
    1.57
     new
    1.56
     an
    1.55
    Activations Density 1.191%

    No Known Activations