© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 54755
    Prev
    Next
    INDEX
    Explanations

    time related words

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

    time, delay, and frequency

    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
    UGS
    0.46
     reelection
    0.44
     adal
    0.44
     justifiable
    0.43
    抜群
    0.43
     inauguration
    0.42
     त्रास
    0.42
    <unused2153>
    0.42
    昭和
    0.42
     குறை
    0.41
    POSITIVE LOGITS
     Chron
    0.49
    TIMER
    0.49
     TIMER
    0.48
    葙
    0.47
     каждая
    0.46
    ченный
    0.45
    喈
    0.44
    ச்ச
    0.44
     Alarm
    0.44
     Timer
    0.44
    Activations Density 0.000%

    No Known Activations