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. 570
    Prev
    Next
    INDEX
    Explanations

    xml content

    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
     المم
    0.64
    master
    0.58
    endom
    0.57
    懐
    0.57
    निश्ड
    0.57
    bull
    0.56
    fs
    0.56
     Except
    0.55
    █
    0.55
    fa
    0.55
    POSITIVE LOGITS
     行政
    0.84
     ute
    0.80
     inqui
    0.74
     类
    0.74
     injections
    0.72
     .(
    0.72
    ValueLayout
    0.72
     máy
    0.71
     cla
    0.71
     tắm
    0.71
    Activations Density 0.000%

    No Known Activations