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. 47152
    Prev
    Next
    INDEX
    Explanations

    visual or technical concepts

    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
     vilket
    0.99
     tots
    0.98
    тни
    0.93
    딕
    0.93
    orsunuz
    0.92
     Auf
    0.92
     datas
    0.91
    ECT
    0.91
    datad
    0.91
    搪
    0.90
    POSITIVE LOGITS
     poaching
    1.17
     Jetty
    1.16
    異なる
    1.15
     rekind
    1.14
     hegemony
    1.13
    異なります
    1.12
     JPEG
    1.12
     Invisalign
    1.11
    Streak
    1.11
     github
    1.10
    Activations Density 0.001%

    No Known Activations