© 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. 141391
    Prev
    Next
    INDEX
    Explanations

    introduced spills sufferers

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

    acknowledging, ignoring, beyond compliance

    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
    悴
    0.50
     sauvegard
    0.48
    ocompat
    0.48
     diminue
    0.47
     multiplicação
    0.46
     faded
    0.45
     revanche
    0.44
     elseif
    0.44
     reicht
    0.44
    níky
    0.44
    POSITIVE LOGITS
     L
    0.56
     Debra
    0.52
     B
    0.52
     C
    0.50
     U
    0.49
     Seven
    0.49
     R
    0.49
     Commissioner
    0.49
     Senior
    0.49
     Henrietta
    0.49
    Activations Density 0.000%

    No Known Activations