© 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. 166801
    Prev
    Next
    INDEX
    Explanations

    harm nursing baby

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

    flight booking, JSX, understanding

    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
    افي
    0.46
     (
    0.45
    ULATION
    0.43
     Carte
    0.42
     Trevelyan
    0.42
    ي
    0.42
    ^{(
    0.41
    edizione
    0.41
    achten
    0.40
     eder
    0.40
    POSITIVE LOGITS
     bitches
    0.52
     KGB
    0.49
     বিরোধী
    0.49
     moim
    0.49
     Chevy
    0.48
     hii
    0.48
     おはよう
    0.48
    থার
    0.47
     ACLU
    0.47
     꿈
    0.47
    Activations Density 0.000%

    No Known Activations