© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30189
    Prev
    Next
    INDEX
    Explanations

    multiplied by

    np_acts-logits-general · gemini-2.5-flash-lite

    percentage calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    rierte
    0.52
     맛있
    0.52
    muş
    0.49
    ני
    0.47
    itiers
    0.46
    örter
    0.46
    לה
    0.44
    褴
    0.44
    тин
    0.44
     анти
    0.44
    POSITIVE LOGITS
     sma
    0.46
     approximately
    0.46
     xw
    0.46
     Timing
    0.46
     pohyb
    0.45
    UVW
    0.43
     uj
    0.43
     cw
    0.43
     hundreds
    0.42
     KV
    0.42
    Activations Density 0.001%

    No Known Activations