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. 17-GEMMASCOPE-2-RES-65K
    4. 2055
    Prev
    Next
    INDEX
    Explanations

    out of or right now

    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_17_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
    ferences
    0.63
    ات
    0.58
     shower
    0.58
    𝒔
    0.53
    pathetic
    0.52
    ત્મક
    0.51
    ओं
    0.50
    organisms
    0.50
    versive
    0.50
    elevation
    0.50
    POSITIVE LOGITS
    არ
    0.64
     darn
    0.64
     xScale
    0.62
     damn
    0.60
    র্ড
    0.57
    кти
    0.56
     banged
    0.55
    গু
    0.54
    ل
    0.54
    gün
    0.53
    Activations Density 0.248%

    No Known Activations