© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5202
    Prev
    Next
    INDEX
    Explanations

    Micro-LED Display, Flint Generals, Russian Antique, Sterling Service, long hairstyles

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

    chat botpythonelectrocardiogramAirportRNAProofDisplayswitchpassportClub

    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
    _______________
    0.35
    _____________
    0.34
    ____________
    0.34
     당신
    0.33
    ________________
    0.32
    投资者
    0.32
    您
    0.32
    游客
    0.32
    开发者
    0.31
    ______________
    0.31
    POSITIVE LOGITS
    pls
    0.39
    gazebo
    0.39
    ント
    0.39
    govt
    0.38
    ital
    0.37
     […]
    0.37
    ifiz
    0.37
     टिप्स
    0.37
    𝘇
    0.37
    ugh
    0.36
    Activations Density 0.134%

    No Known Activations