© 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. 88247
    Prev
    Next
    INDEX
    Explanations

    pm followed by punctuation or days

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

    morning time markers

    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
     noct
    0.63
    evening
    0.63
    dinner
    0.63
     nighttime
    0.59
     夜
    0.57
     کھانا
    0.57
    a
    0.55
     nocturnal
    0.54
    nacht
    0.52
     इवनिंग
    0.52
    POSITIVE LOGITS
    .,
    0.57
    ၊
    0.53
     ၊
    0.53
    बी
    0.52
    ONG
    0.52
     ،
    0.50
    rs
    0.48
     ขั้น
    0.48
     เชื่อ
    0.48
    ED
    0.48
    Activations Density 0.028%

    No Known Activations