© 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. 5044
    Prev
    Next
    INDEX
    Explanations

    Import, Load, Install

    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
    这些人
    0.43
    idefinite
    0.42
     þis
    0.42
    -'+
    0.41
     ĝi
    0.41
     denna
    0.41
     sfrutt
    0.40
     është
    0.39
    comodule
    0.39
     aquesta
    0.39
    POSITIVE LOGITS
     the
    0.81
     an
    0.53
     a
    0.52
     all
    0.46
     Sh
    0.46
     The
    0.45
     your
    0.44
     Global
    0.43
    一个
    0.43
     International
    0.43
    Activations Density 0.003%

    No Known Activations