© 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. 22101
    Prev
    Next
    INDEX
    Explanations

    copy stream

    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
    ރ
    0.45
    DVD
    0.44
     giallo
    0.43
     DVDs
    0.43
     playlists
    0.42
     Frozen
    0.42
     Cinema
    0.41
    鲽
    0.41
     ffm
    0.41
     DVD
    0.40
    POSITIVE LOGITS
     copying
    0.51
     копи
    0.50
     copiar
    0.47
     copier
    0.47
     कॉपी
    0.46
     copy
    0.43
     cop
    0.41
     কপি
    0.40
     copied
    0.40
     copi
    0.40
    Activations Density 0.003%

    No Known Activations