© 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. 199048
    Prev
    Next
    INDEX
    Explanations

    spinoff channels

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

    XML formatting

    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
    KP
    0.47
    ^^
    0.47
     لق
    0.45
    治療
    0.44
     جبکہ
    0.44
     توسط
    0.43
     الوق
    0.43
    oba
    0.42
     пору
    0.42
    ^^^^
    0.42
    POSITIVE LOGITS
     Hakk
    0.55
     Heartland
    0.52
     எங்களுக்கு
    0.48
     Archdiocese
    0.46
    נגלית
    0.46
    𝓖
    0.46
     Millennials
    0.46
     Aquare
    0.46
     Gewer
    0.45
     Boynton
    0.45
    Activations Density 0.001%

    No Known Activations