© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14299
    Prev
    Next
    INDEX
    Explanations

    current timekeeping and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    છા
    0.83
     بتایا
    0.79
     انجن
    0.75
    FromResult
    0.74
    綎
    0.74
    ինչ
    0.73
    େ
    0.73
    elijkheid
    0.73
    ้า
    0.72
    旣
    0.72
    POSITIVE LOGITS
     ආ
    0.75
    ্যালেঞ্জ
    0.73
     fabrik
    0.70
    aduct
    0.69
     cooperatives
    0.68
     алы
    0.66
     publishers
    0.64
    Dialog
    0.64
     Cooperative
    0.63
     rooftops
    0.62
    Activations Density 0.000%

    No Known Activations