© 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. 39882
    Prev
    Next
    INDEX
    Explanations

    interactive exhibits and themes

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

    interactive exhibits and experiences

    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
    ᠮ
    0.43
    ರುವುದು
    0.42
     Dla
    0.40
     ಅಧಿಕಾರಿ
    0.40
     Colts
    0.39
     Xmas
    0.39
     ವಿಧಾನಸಭಾ
    0.39
     Maturity
    0.38
     ለእ
    0.38
    苌
    0.38
    POSITIVE LOGITS
    Interactive
    0.56
     interactive
    0.54
    interactive
    0.50
     Interactive
    0.49
     immersive
    0.49
    immersive
    0.47
    体验
    0.45
     interactivity
    0.45
     simulated
    0.44
     choreographed
    0.44
    Activations Density 0.082%

    No Known Activations