© 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. 189163
    Prev
    Next
    INDEX
    Explanations

    non-english languages

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

    long python snakes

    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
    âng
    0.53
     $-\
    0.47
    urig
    0.46
     `-
    0.45
    рены
    0.45
     (${
    0.44
     °
    0.44
     revest
    0.44
     (-
    0.44
    ।-
    0.43
    POSITIVE LOGITS
     République
    0.51
     पढ़ाने
    0.49
    に取り組
    0.49
     खोजने
    0.48
     सुनने
    0.47
     ಇದು
    0.46
    一個
    0.45
     মুখের
    0.45
     امرأة
    0.44
    コンピュー
    0.44
    Activations Density 0.001%

    No Known Activations