© 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. 3032
    Prev
    Next
    INDEX
    Explanations

    stock markets, fiction, screen

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

    topic-defining content words—primarily salient nouns and key adjectives—that signal the main subjects or entities of a prompt, including explicit or highly charged topics.

    oai_token-act-pair · gpt-5
    Triggered 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
    Negative Logits
    ält
    0.33
    သုံးပြု
    0.33
    transform
    0.32
     Chávez
    0.31
     মাংস
    0.31
    filename
    0.30
     सार्वजनिक
    0.30
     Hazardous
    0.30
    <unused1038>
    0.30
    parser
    0.30
    POSITIVE LOGITS
     اجمعين
    0.31
    ،
    0.31
     richesse
    0.30
     اش
    0.30
    ."
    0.29
    .
    0.29
     اف
    0.29
    ؟
    0.29
    شم
    0.28
     saben
    0.28
    Activations Density 1.264%

    No Known Activations