© 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. 211443
    Prev
    Next
    INDEX
    Explanations

    time comparison

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

    abstract time concepts

    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
    ┙
    0.52
    ту
    0.51
    푸
    0.50
     promu
    0.48
     fumar
    0.48
     afficher
    0.48
     ।
    0.46
    ফু
    0.46
    <0x9E>
    0.46
    ।
    0.46
    POSITIVE LOGITS
    Time
    0.54
     Time
    0.51
     Times
    0.47
    Mo
    0.46
    timers
    0.46
     أمام
    0.45
    Tim
    0.45
     时间
    0.44
     Tunes
    0.44
     TIME
    0.44
    Activations Density 0.000%

    No Known Activations