© 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. 121768
    Prev
    Next
    INDEX
    Explanations

    time phrases

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

    time series and date

    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
    垁
    0.59
     Dord
    0.55
    লাপ
    0.52
    ベビー
    0.52
    nés
    0.52
     ม
    0.51
    वानी
    0.51
    h
    0.51
     ク
    0.50
     ส
    0.49
    POSITIVE LOGITS
    ’
    0.51
    륙
    0.47
     fringilla
    0.46
     catheters
    0.46
    time
    0.46
     tenfold
    0.43
     stylesheet
    0.43
     bogey
    0.42
     политика
    0.41
    期間限定
    0.41
    Activations Density 0.020%

    No Known Activations