© 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. 176315
    Prev
    Next
    INDEX
    Explanations

    catfish bite

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

    local descriptions and conditions

    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
    حدة
    0.48
     sécr
    0.48
     aktuell
    0.45
    Buddhist
    0.43
     tiêu
    0.42
    ất
    0.41
    ’
    0.41
     Buddhist
    0.40
     Pyongyang
    0.40
    eldorf
    0.40
    POSITIVE LOGITS
     answering
    0.54
    ।.
    0.50
     opting
    0.46
     ہم
    0.45
     첫
    0.45
     candidat
    0.45
    হইয়া
    0.45
     especially
    0.44
     especiales
    0.44
     advis
    0.44
    Activations Density 0.000%

    No Known Activations