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. 22-GEMMASCOPE-2-RES-65K
    4. 3487
    Prev
    Next
    INDEX
    Explanations

    free and specific

    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_22_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
     كبير
    0.63
     كانت
    0.59
     كبيرة
    0.58
     جديدة
    0.55
     spezielle
    0.55
    د
    0.55
     cơ
    0.55
     ulike
    0.55
    があります
    0.54
    新
    0.54
    POSITIVE LOGITS
     концу
    0.43
    ravity
    0.42
     persecution
    0.42
    üllen
    0.41
     haciendo
    0.41
    Epoch
    0.40
    coln
    0.40
    于
    0.40
    ibert
    0.40
    ipun
    0.39
    Activations Density 0.143%

    No Known Activations