© 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. 150176
    Prev
    Next
    INDEX
    Explanations

    in household cleaning

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

    combining wind

    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
    Not in Any Lists

    No Comments

    Negative Logits
     日本製
    0.53
    <unused1094>
    0.50
     parol
    0.49
     感じ
    0.48
     ሰ
    0.48
     ባ
    0.47
    ሮች
    0.47
     നടപ
    0.47
     જાય
    0.47
     那麼
    0.47
    POSITIVE LOGITS
    src
    0.51
     atherosclerosis
    0.47
    sss
    0.46
    MOT
    0.45
    frying
    0.45
     upper
    0.45
    begin
    0.45
    ulling
    0.45
    1
    0.44
    充足
    0.44
    Activations Density 0.000%

    No Known Activations