© 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. 207097
    Prev
    Next
    INDEX
    Explanations

    specified interface

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

    . lawyer circle busy

    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
    I
    0.53
    畨
    0.50
     UNITS
    0.49
    Mast
    0.48
    Gust
    0.47
     remarkably
    0.46
     موسی
    0.45
     পরি
    0.45
    عکس
    0.45
    <unused544>
    0.44
    POSITIVE LOGITS
    (
    0.55
    라는
    0.48
     cancerous
    0.47
     spring
    0.47
     specified
    0.47
     delineated
    0.46
     aircraft
    0.46
     siege
    0.44
     elliptical
    0.44
     warranty
    0.44
    Activations Density 0.001%

    No Known Activations