© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 5923
    Prev
    Next
    INDEX
    Explanations

    device or code

    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
    วน
    0.38
     erreur
    0.38
    エラー
    0.38
    crossentropy
    0.38
     দৃঢ়
    0.36
    消毒
    0.36
    প
    0.35
    第四
    0.35
     ആരംഭ
    0.35
    潢
    0.35
    POSITIVE LOGITS
     Digit
    0.37
     Mortal
    0.35
     tom
    0.35
     Tome
    0.35
     tomb
    0.35
     digital
    0.35
     byte
    0.34
     SMA
    0.34
     usurp
    0.34
     Edited
    0.34
    Activations Density 0.001%

    No Known Activations