© 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. 192372
    Prev
    Next
    INDEX
    Explanations

    located there

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

    refusal of inappropriate requests

    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
    ixels
    0.52
    Anchor
    0.49
    be
    0.47
    moor
    0.46
    R
    0.45
     gage
    0.45
    ie
    0.45
     creeping
    0.44
    EOS
    0.44
    X
    0.43
    POSITIVE LOGITS
    ک
    0.53
     abhor
    0.52
     อิ
    0.51
     woh
    0.50
     заня
    0.50
     ک
    0.50
     بنیادی
    0.49
     പദ്ധതി
    0.49
    લિક
    0.49
    čenje
    0.48
    Activations Density 0.001%

    No Known Activations