© 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. 34-GEMMASCOPE-RES-131K
    7. 58756
    Prev
    Next
    INDEX
    Explanations

    tokens starting with se

    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_34/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
    轍
    -0.97
    動機
    -0.93
    などが
    -0.86
    を
    -0.85
     Wieder
    -0.83
    後は
    -0.80
    態度
    -0.80
     åter
    -0.77
     concurrently
    -0.77
    ～～
    -0.77
    POSITIVE LOGITS
    Se
    1.41
     Se
    1.41
     Се
    1.23
    Се
    1.19
    えっ
    1.13
     seques
    1.09
     segregated
    1.09
     Seg
    1.06
     sequestration
    1.04
     SE
    1.02
    Activations Density 0.053%

    No Known Activations