© 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. 22252
    Prev
    Next
    INDEX
    Explanations

    explaining or defining terms

    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
    Ꭻ
    0.42
     वगैर
    0.41
     الاسلام
    0.41
    াঙ্গা
    0.41
    অব
    0.37
    ۍ
    0.37
    ୦
    0.37
    ாவை
    0.36
    NJ
    0.36
     कर्मी
    0.36
    POSITIVE LOGITS
    也就是
    0.60
     همان
    0.58
     called
    0.55
     cioè
    0.52
     "
    0.50
     sogen
    0.50
    所謂
    0.50
     sogenannte
    0.50
     অর্থাৎ
    0.49
    所谓的
    0.49
    Activations Density 0.002%

    No Known Activations