© 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. 31-GEMMASCOPE-2-RES-262K
    7. 3164
    Prev
    Next
    INDEX
    Explanations

    code, punctuation, and symbols

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

    quoted or otherwise highlighted text fragments—especially all-caps headings/acronyms and the specific substrings referenced in editing or replace commands.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مليار
    0.23
    "+"|".
    0.21
     Milliarden
    0.21
     voluntad
    0.21
     magasins
    0.21
     huit
    0.21
    купно
    0.21
    yemek
    0.20
    نګ
    0.20
    𒍣
    0.20
    POSITIVE LOGITS
    ↵
    0.28
     {
    0.25
              
    0.23
     {/*
    0.23
     That
    0.22
     //
    0.22
     I
    0.21
    <0xE3>
    0.21
     \
    0.20
     ('
    0.20
    Activations Density 1.387%

    No Known Activations