© 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. 206460
    Prev
    Next
    INDEX
    Explanations

    judgments obtained, there on, So meet

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

    City Limits, Research, Sanitation, Chef

    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
     besondere
    0.45
    年至
    0.45
     irgend
    0.45
    સા
    0.42
    佂
    0.42
    emberg
    0.42
    కునే
    0.42
     leisten
    0.42
    atories
    0.42
     commotion
    0.42
    POSITIVE LOGITS
    u
    0.59
     sony
    0.56
    OPTIONS
    0.52
    Sony
    0.52
    al
    0.51
    battery
    0.51
    Battery
    0.50
    Kayak
    0.50
    Lovely
    0.49
    Happy
    0.49
    Activations Density 0.001%

    No Known Activations