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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 41318
    Prev
    Next
    INDEX
    Explanations

    jalapeño variations

    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
     bool
    0.76
    粛
    0.72
    SIC
    0.70
     الجديدة
    0.69
     Offensive
    0.68
     offensive
    0.66
    স্তন
    0.66
     herb
    0.66
    류
    0.65
     gang
    0.65
    POSITIVE LOGITS
    пень
    0.79
    샌
    0.73
    па
    0.73
    缙
    0.72
    oggia
    0.71
    ape
    0.69
    নীতি
    0.68
    പ്പോ
    0.67
    apa
    0.67
    ouses
    0.67
    Activations Density 0.002%

    No Known Activations