© 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. 68768
    Prev
    Next
    INDEX
    Explanations

    On-line translation

    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
    玉ねぎ
    -0.96
    oda
    -0.95
     COVID
    -0.93
    かも知
    -0.92
    因为它
    -0.92
    と思っていた
    -0.92
     Selv
    -0.92
    광
    -0.92
    in
    -0.91
     plastiques
    -0.91
    POSITIVE LOGITS
     and
    1.50
     that
    1.20
    Cartney
    1.13
     bych
    1.07
    styleType
    1.06
     choroby
    1.03
     cachorros
    1.03
    Soporte
    1.01
    ufnahme
    1.00
     kommunik
    0.99
    Activations Density 0.000%

    No Known Activations