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. 1294
    Prev
    Next
    INDEX
    Explanations

    health services administration

    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
     ๆ
    0.65
     ther
    0.63
    തം
    0.61
     ret
    0.61
    ่ง
    0.60
    पन
    0.58
     Ян
    0.58
     hra
    0.58
    th
    0.57
    TERN
    0.57
    POSITIVE LOGITS
     ابھی
    0.74
     derby
    0.68
    Arth
    0.68
    🠀
    0.67
    覷
    0.66
    ಸ್ತಕ
    0.66
    enziali
    0.66
    麴
    0.65
    Nom
    0.65
     serialization
    0.64
    Activations Density 0.029%

    No Known Activations