© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 3922
    Prev
    Next
    INDEX
    Explanations

    active, warm, and bright

    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_all/layer_41_width_262k_l0_big
    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
    َان
    0.51
    ោម
    0.50
    ាតុ
    0.50
    ាប
    0.50
    ្នែក
    0.48
    ﻪ
    0.47
    รรม
    0.47
    brightness
    0.47
     এইরূপে
    0.47
    ួរ
    0.47
    POSITIVE LOGITS
     unapolog
    0.48
    in
    0.42
     бушлай
    0.41
     Museum
    0.41
     Financ
    0.40
     Nietzsche
    0.40
    들
    0.40
    Leggi
    0.39
     Graffiti
    0.39
     Tolkien
    0.39
    Activations Density 0.031%

    No Known Activations