© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 3543
    Prev
    Next
    INDEX
    Explanations

    sharing

    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_53_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
    諭
    0.37
    珢
    0.36
    ദ്ര
    0.35
    幌
    0.35
     தட
    0.34
    ниците
    0.33
    㶪
    0.32
     दम
    0.31
    rául
    0.31
    ründ
    0.31
    POSITIVE LOGITS
     share
    4.03
     sharing
    4.03
     공유
    3.95
     shared
    3.83
     condiv
    3.83
     Share
    3.69
    Share
    3.69
     Sharing
    3.69
    共享
    3.67
    share
    3.64
    Activations Density 0.220%

    No Known Activations