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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 41384
    Prev
    Next
    INDEX
    Explanations

    1(

    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_65k_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
     ।”
    0.76
     ৷
    0.71
    Args
    0.68
     аргу
    0.68
    סי
    0.66
    ‌.
    0.66
    ⵏ
    0.66
    Dest
    0.65
     ፣
    0.65
    ামীর
    0.64
    POSITIVE LOGITS
     впечатление
    0.74
     Επι
    0.73
    आरटी
    0.73
     vine
    0.70
    crose
    0.69
     ẞ
    0.69
     Resistant
    0.69
     creciendo
    0.69
     resistant
    0.68
    enio
    0.68
    Activations Density 0.012%

    No Known Activations