© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6621
    Prev
    Next
    INDEX
    Explanations

    few, lot, result, solution, surging

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

    how to run code

    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_53_width_65k_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
     WATCH
    0.46
    WATCH
    0.43
    у
    0.43
     NONINFRINGEMENT
    0.43
     午
    0.40
     ERA
    0.40
     Watch
    0.39
    う
    0.38
     outer
    0.38
     Ongoing
    0.37
    POSITIVE LOGITS
     protracted
    0.67
     terrific
    0.61
     superb
    0.57
     couple
    0.56
     few
    0.54
     lot
    0.54
    foresaid
    0.52
     variety
    0.51
     huge
    0.50
     fantastic
    0.48
    Activations Density 0.070%

    No Known Activations