© 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-262K
    7. 26778
    Prev
    Next
    INDEX
    Explanations

    questions and jokes

    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_262k_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
    %%%%%%%%%%%%
    0.25
    MouseMove
    0.25
     hypothesize
    0.25
    想像
    0.24
    Fancy
    0.23
    䀒
    0.23
     বক্ত
    0.23
     vielfält
    0.23
    зіно
    0.23
    രിക്കുന്നത്
    0.23
    POSITIVE LOGITS
     の
    0.27
    nc
    0.26
     ‎
    0.26
    ‎
    0.26
     then
    0.25
    gg
    0.25
    ᴀ
    0.25
    5
    0.25
    ien
    0.25
     nationale
    0.24
    Activations Density 0.000%

    No Known Activations