© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10091
    Prev
    Next
    INDEX
    Explanations

    taking time or duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
    IMENTAL
    0.86
    푐
    0.85
     kuul
    0.85
     giãn
    0.84
    ску
    0.84
    EventHandler
    0.82
    현
    0.82
     फॉलोइंग
    0.82
     proch
    0.80
    푚
    0.79
    POSITIVE LOGITS
     take
    4.56
    take
    4.38
     taken
    4.29
     Take
    4.25
    Take
    4.19
     taking
    4.18
    taking
    4.07
     takes
    4.05
     Taking
    3.99
    taken
    3.98
    Activations Density 1.048%

    No Known Activations