© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2905
    Prev
    Next
    INDEX
    Explanations

    code directives and hashtags

    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/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     nyingi
    0.44
    บค้น
    0.40
    
    0.39
     पुस्तिका
    0.39
     gravité
    0.38
     دی۔
    0.38
    渕
    0.36
     गुणा
    0.36
     restriction
    0.36
     adipis
    0.36
    POSITIVE LOGITS
    MeToo
    0.93
     #
    0.85
    ️⃣
    0.76
    ,#
    0.75
     \#
    0.73
    \#
    0.72
    ifdef
    0.72
    .#
    0.72
    -#
    0.72
    hashtag
    0.71
    Activations Density 0.019%

    No Known Activations