© 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. 102873
    Prev
    Next
    INDEX
    Explanations

    marketplace fordiagrams oftakes placeGMB profile

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

    Old Man Tiber

    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
    頡
    0.60
     চারটি
    0.54
     combate
    0.53
     અથવા
    0.51
    ାନ
    0.51
    Ἠ
    0.51
    頴
    0.50
    㜌
    0.50
    䪲
    0.50
    嬙
    0.49
    POSITIVE LOGITS
    t
    0.57
    m
    0.54
    ero
    0.52
    :
    0.51
    vi
    0.49
    !
    0.49
    ;
    0.49
    y
    0.48
    k
    0.48
    £
    0.48
    Activations Density 0.000%

    No Known Activations