© 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. 184974
    Prev
    Next
    INDEX
    Explanations

    replacements

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

    historical explanations for fairness

    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
    ዬ
    0.46
    ਨੀ
    0.45
     ಪಕ್ಷ
    0.44
     гале
    0.44
     widths
    0.43
    でに
    0.42
     stationary
    0.42
    eleration
    0.42
    izontal
    0.41
     chiều
    0.41
    POSITIVE LOGITS
     своїх
    0.55
     Screenshots
    0.45
     Offenders
    0.43
    彼
    0.43
    Ahmed
    0.42
     своих
    0.42
    痛
    0.41
     YOUR
    0.41
     Tasting
    0.41
     MEET
    0.41
    Activations Density 0.000%

    No Known Activations