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. 41312
    Prev
    Next
    INDEX
    Explanations

    addresses and forms

    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
     मोह
    0.83
     দাগ
    0.79
     வச
    0.75
    ෝග
    0.74
    érable
    0.74
     対象
    0.73
    oggetto
    0.73
    易
    0.71
     предприятия
    0.69
    urados
    0.69
    POSITIVE LOGITS
    ี้ยว
    0.89
    Aux
    0.76
    を中心に
    0.72
     Endowment
    0.72
    雔
    0.71
     পেতে
    0.71
     Aux
    0.70
     execution
    0.70
     auxiliary
    0.69
     curves
    0.69
    Activations Density 0.001%

    No Known Activations