© 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. 142917
    Prev
    Next
    INDEX
    Explanations

    through unlimited or multiple

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

    handles both

    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
    0.61
     Sum
    0.54
     Middle
    0.54
     May
    0.50
     Der
    0.50
     ${
    0.49
     Müdür
    0.49
     Western
    0.49
     businessman
    0.48
     .
    0.48
    POSITIVE LOGITS
    hopping
    0.67
    npcs
    0.57
    akke
    0.56
    agamanam
    0.56
    awai
    0.54
    orgh
    0.54
    arcade
    0.54
    iót
    0.54
    UTTON
    0.53
    etra
    0.53
    Activations Density 0.000%

    No Known Activations