© 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. 185192
    Prev
    Next
    INDEX
    Explanations

    creator, heir, designer, send, best

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

    always subjective lists

    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
     ձ
    0.55
    '
    0.49
     dispone
    0.46
    ச்செ
    0.45
    )
    0.45
     plomb
    0.45
    uisce
    0.44
    ania
    0.43
    ட்டின்
    0.43
     conspicuous
    0.43
    POSITIVE LOGITS
    …。
    0.50
     Leung
    0.48
     Lockdown
    0.46
    费用
    0.45
    %。
    0.45
     evoked
    0.44
    瑆
    0.42
     নিরাপত্তার
    0.42
    群众
    0.42
     frauds
    0.42
    Activations Density 0.000%

    No Known Activations