© 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. 201513
    Prev
    Next
    INDEX
    Explanations

    biblical references and place names

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

    Geralt of Rivia

    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
    գ
    0.46
     implementations
    0.44
     పథ
    0.43
    "/
    0.42
     yaklaş
    0.42
     kilometre
    0.42
     impairment
    0.41
    stantial
    0.41
     onem
    0.41
     ö
    0.41
    POSITIVE LOGITS
    PKG
    0.45
    生意
    0.44
     dibuat
    0.42
     Kabul
    0.42
    Atlet
    0.42
     अपनी
    0.41
     جای
    0.41
     Rajput
    0.41
    शिया
    0.41
    छोटी
    0.41
    Activations Density 0.000%

    No Known Activations