© 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. 203011
    Prev
    Next
    INDEX
    Explanations

    independent candidate

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

    player in an adventure

    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
     revital
    0.49
    ;
    0.46
     Nutrition
    0.46
     compartil
    0.45
     Prefer
    0.44
     &
    0.44
    。
    0.44
     -
    0.43
     CRC
    0.42
    ,
    0.41
    POSITIVE LOGITS
    であろう
    0.60
    КА
    0.55
    kében
    0.50
    语句
    0.50
    現在は
    0.50
    ወ
    0.49
    ungkinan
    0.49
     విధంగా
    0.48
     ظِلِّ
    0.47
    దం
    0.46
    Activations Density 0.001%

    No Known Activations