© 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. 9591
    Prev
    Next
    INDEX
    Explanations

    Michael Jordan

    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
     élytres
    0.49
    ratingBarStyle
    0.48
    IRCONIUM
    0.48
    aggable
    0.45
    ချင်း
    0.45
     %>.
    0.44
     vésicules
    0.43
     ਲੋ
    0.43
    楲
    0.43
     ionizing
    0.43
    POSITIVE LOGITS
     Microsoft
    0.71
    angelo
    0.71
    Microsoft
    0.62
     Mike
    0.62
    Mike
    0.55
     Michael
    0.49
     Xbox
    0.49
     Mic
    0.48
     Office
    0.46
     mic
    0.46
    Activations Density 0.007%

    No Known Activations