© 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. 64673
    Prev
    Next
    INDEX
    Explanations

    css @ include function keywords

    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
     Finances
    0.41
    푀
    0.40
     Pairs
    0.40
     Printable
    0.40
     Languages
    0.38
     Dispose
    0.38
    象棋
    0.38
     Assets
    0.38
     Equal
    0.38
    Denovo
    0.37
    POSITIVE LOGITS
    竞
    0.40
    ˑ
    0.40
     க
    0.40
    न्ह
    0.39
    xb
    0.39
    XB
    0.39
    விக்க
    0.39
    躡
    0.38
     पद्ध
    0.38
     elastic
    0.38
    Activations Density 0.000%

    No Known Activations