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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 47104
    Prev
    Next
    INDEX
    Explanations

    concepts or descriptions

    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
    ்ச
    1.07
     Tìm
    1.03
     zabud
    1.03
    سر
    1.03
    Բ
    0.97
    リース
    0.96
    Material
    0.95
    ỹ
    0.95
     கிழக்கு
    0.94
     stycznia
    0.93
    POSITIVE LOGITS
    opathy
    1.19
     hoarding
    1.18
    hary
    1.17
    нном
    1.13
    ueling
    1.12
    enriched
    1.11
     hiring
    1.10
     naming
    1.10
     internalization
    1.10
     monitoring
    1.09
    Activations Density 0.001%

    No Known Activations