© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 59890
    Prev
    Next
    INDEX
    Explanations

    screen distance or duration

    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
    埂
    0.42
     Tsh
    0.36
     segments
    0.36
     Bloc
    0.36
     rè
    0.35
    很多
    0.35
     Rocca
    0.34
    વાલ
    0.34
    কমার
    0.34
     interiores
    0.33
    POSITIVE LOGITS
    Mathematics
    0.44
     Mathematics
    0.41
     एडवा
    0.40
    數學
    0.40
    畠
    0.40
     электри
    0.38
    飽
    0.38
     هون
    0.38
     Improvement
    0.38
    ಲ್‌
    0.38
    Activations Density 0.000%

    No Known Activations