© 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. 83589
    Prev
    Next
    INDEX
    Explanations

    county, subdirectory, its, 7 lot, purpose, highest

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

    game specific

    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
    आ
    0.55
     obiettivo
    0.54
    Vý
    0.52
    sortBy
    0.52
     റിപ്പോ
    0.50
    扆
    0.50
    Przyp
    0.49
     કબ
    0.49
     Го
    0.48
    晉
    0.48
    POSITIVE LOGITS
     mell
    0.53
     curtailed
    0.50
    өт
    0.49
     fung
    0.48
     truncated
    0.46
    :";
    0.45
     gr
    0.45
     applied
    0.45
     sanit
    0.43
    HttpMessage
    0.43
    Activations Density 0.001%

    No Known Activations