© 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. 77392
    Prev
    Next
    INDEX
    Explanations

    phrases starting with today's

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

    today's date, day, weather

    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
    ეგისტრ
    0.51
    窒
    0.47
     pédicule
    0.46
    사각형
    0.44
     மேற்பர
    0.43
    timeslots
    0.43
     زینت
    0.42
    يمة
    0.42
    پيديا
    0.42
    書類
    0.42
    POSITIVE LOGITS
    ){
    0.48
    ()){
    0.48
     example
    0.47
    isting
    0.46
    NY
    0.46
    anol
    0.45
     today
    0.44
     QUE
    0.44
    breeds
    0.44
     was
    0.44
    Activations Density 0.002%

    No Known Activations