© 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. 14715
    Prev
    Next
    INDEX
    Explanations

    have to

    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
     adanya
    0.81
     باقی
    0.80
    浱
    0.80
     ናቸው
    0.78
    taining
    0.77
     વધારે
    0.77
     |.
    0.76
    আমরা
    0.76
    جموعة
    0.75
    ަރ
    0.74
    POSITIVE LOGITS
     to
    1.33
    要
    1.21
    ต้อง
    1.20
     να
    1.18
     phải
    1.07
    ToBe
    0.98
     jā
    0.97
     To
    0.94
    to
    0.91
     要
    0.87
    Activations Density 0.015%

    No Known Activations