Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 53023
    Prev
    Next
    INDEX
    Explanations

    Korean, Taiwan, graphics, behold

    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_29_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
     очереди
    0.80
    राजा
    0.76
    正在
    0.74
    悻
    0.74
    انے
    0.74
     झू
    0.73
     ay
    0.73
    venta
    0.73
    引擎
    0.72
    ओम
    0.72
    POSITIVE LOGITS
    とも
    0.80
     biết
    0.74
     Weed
    0.72
     handic
    0.69
    హిత
    0.68
    可知
    0.67
     Graphics
    0.66
    殘
    0.66
     behold
    0.66
     মধ্য
    0.66
    Activations Density 0.000%

    No Known Activations