© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 56692
    Prev
    Next
    INDEX
    Explanations

    rape, incest, voter registration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Governor
    0.43
     tung
    0.41
     Provinces
    0.41
     Figure
    0.39
     prop
    0.39
     guiding
    0.39
     गव
    0.39
     Proposition
    0.38
     B
    0.38
     Dolphin
    0.38
    POSITIVE LOGITS
    یدم
    0.43
    ALCHEMY
    0.43
    ENDMENT
    0.42
    Straw
    0.42
    <unused1842>
    0.42
    Фото
    0.42
    ಠ
    0.41
     потрі
    0.41
    ینک
    0.41
    Castle
    0.41
    Activations Density 0.000%

    No Known Activations