© 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. 9807
    Prev
    Next
    INDEX
    Explanations

    date and time qualifiers

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

    times and dates

    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
    читы
    0.46
    '>
    0.37
     इसकी
    0.37
    ‑
    0.37
     Passive
    0.36
     取り
    0.36
    '>"
    0.36
    '>{
    0.35
     premise
    0.35
    content
    0.35
    POSITIVE LOGITS
    녘
    0.45
    㼛
    0.43
    තර
    0.42
     rétrécies
    0.42
    تاریخ
    0.42
    㛲
    0.41
    瑗
    0.41
    ടതി
    0.40
     Владимир
    0.40
     calendrier
    0.40
    Activations Density 0.003%

    No Known Activations