© 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. 53484
    Prev
    Next
    INDEX
    Explanations

    time duration in years

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

    duration in years ending now

    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
     decades
    0.66
     décadas
    0.54
     Jahrze
    0.53
    Years
    0.51
    years
    0.49
    ABLISHED
    0.49
    所
    0.48
     década
    0.48
    ע
    0.48
    ো
    0.46
    POSITIVE LOGITS
     หนึ่ง
    0.64
     오늘은
    0.57
     বর্তমানে
    0.55
     현재
    0.55
     diantaranya
    0.54
     இதுவரை
    0.54
     сейчас
    0.54
     सध्या
    0.54
     attualmente
    0.54
     derzeit
    0.52
    Activations Density 0.031%

    No Known Activations