© 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. 99456
    Prev
    Next
    INDEX
    Explanations

    examples, code, and technical 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
     spiders
    0.42
     sneezing
    0.42
    Ast
    0.40
     handheld
    0.39
    轸
    0.39
     hesitant
    0.39
    Gew
    0.39
    害
    0.38
    ڄ
    0.38
    herent
    0.38
    POSITIVE LOGITS
    xmlns
    0.38
     Pore
    0.37
    startswith
    0.36
    题目
    0.36
     文
    0.35
     দেখতে
    0.34
    初心
    0.34
     STEP
    0.33
    LAND
    0.33
    adena
    0.33
    Activations Density 0.003%

    No Known Activations