© 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. 159917
    Prev
    Next
    INDEX
    Explanations

    steel holding corporation

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

    Parmes*an* is; Family Fun; monstrous beings; household_id; direct leak; with templates

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ，
    0.47
     ，
    0.43
    +$
    0.42
     सेंटर
    0.42
     pus
    0.42
     hamburger
    0.42
    달
    0.41
     მნიშვნელ
    0.41
     باغ
    0.41
     크게
    0.41
    POSITIVE LOGITS
    зи
    0.55
    цо
    0.54
    ﻌ
    0.53
    ти
    0.45
    Hazard
    0.45
     ബാല
    0.44
    ynaptic
    0.43
    ри
    0.43
    क्रमा
    0.43
    ски
    0.43
    Activations Density 0.000%

    No Known Activations