© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 115008
    Prev
    Next
    INDEX
    Explanations

    define and, work with, drive ., very high, pass my, more professional, timely style

    np_acts-logits-general · gemini-2.5-flash-lite

    value, office, fire, gem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )\
    0.54
    ,
    0.52
     of
    0.47
    ,\
    0.46
     trakcie
    0.45
     spur
    0.45
    ),
    0.45
    je
    0.44
     bits
    0.44
    iong
    0.44
    POSITIVE LOGITS
    쌔
    0.63
    윅
    0.50
    鲵
    0.49
    ພວກເຮ
    0.48
    薁
    0.47
     sărb
    0.46
     অর্চনা
    0.46
     newApproved
    0.46
    晫
    0.45
    τικών
    0.45
    Activations Density 0.001%

    No Known Activations