© 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. 31-GEMMASCOPE-2-RES-65K
    7. 45164
    Prev
    Next
    INDEX
    Explanations

    listing versions or options

    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_31_width_65k_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
     R
    0.42
    见面
    0.42
    র্ণ
    0.42
    文档
    0.41
    馏
    0.41
     चा
    0.40
    큥
    0.40
    tor
    0.40
    转发
    0.40
     Sparkling
    0.39
    POSITIVE LOGITS
     landlab
    0.48
    フェ
    0.44
     agrup
    0.43
    ŭ
    0.42
     unmarried
    0.42
     cuma
    0.42
     aap
    0.41
     beragam
    0.41
     agrand
    0.40
     "*");
    0.40
    Activations Density 0.019%

    No Known Activations