© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9353
    Prev
    Next
    INDEX
    Explanations

    function takes arguments

    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/layer_40_width_16k_l0_medium
    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
     `=`
    0.39
    环境变量
    0.38
     subspaces
    0.38
     subcommand
    0.38
    랫
    0.37
    顾问
    0.37
    附加
    0.36
    替换
    0.36
    动态
    0.36
     récup
    0.36
    POSITIVE LOGITS
     accepting
    1.81
     accepts
    1.77
     accept
    1.73
    accept
    1.63
    Accept
    1.58
     acept
    1.58
     Accepting
    1.58
     принима
    1.54
     принимает
    1.54
    接受
    1.50
    Activations Density 0.221%

    No Known Activations