© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39191
    Prev
    Next
    INDEX
    Explanations

    foreign words and mathematical notation

    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
    っているので
    -1.25
     ジップ
    -0.96
    顱
    -0.95
     of
    -0.93
    sibilidad
    -0.93
    変わり
    -0.92
     køb
    -0.91
    っしゃ
    -0.91
    &.
    -0.90
    fører
    -0.89
    POSITIVE LOGITS
    This
    1.02
     barrios
    0.99
    MODO
    0.96
    äger
    0.93
    Aihe
    0.90
    これは
    0.90
     şeyi
    0.87
     Solskjaer
    0.87
    Peers
    0.87
    で
    0.86
    Activations Density 0.053%

    No Known Activations