© 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. 13825
    Prev
    Next
    INDEX
    Explanations

    university of

    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
     célè
    -2.00
     siè
    -1.89
     fidé
    -1.87
    久し
    -1.80
     Matériau
    -1.67
     relâche
    -1.66
    Leírás
    -1.63
     enthou
    -1.59
    patrón
    -1.58
     trône
    -1.58
    POSITIVE LOGITS
    a
    1.97
    o
    1.76
     as
    1.76
    </em>
    1.73
    e
    1.67
     these
    1.65
    '
    1.63
    B
    1.60
    v
    1.57
    P
    1.53
    Activations Density 0.074%

    No Known Activations