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. 47109
    Prev
    Next
    INDEX
    Explanations

    ordinary social 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
    𝘨
    1.24
    ">—
    1.14
     approximated
    1.13
    ladesh
    1.12
     refractive
    1.11
     subclasses
    1.10
     principais
    1.08
    રા
    1.08
    Ⲧ
    1.06
    ϫ
    1.06
    POSITIVE LOGITS
     식으로
    1.19
    öne
    1.14
     সংস্করণ
    1.08
     wording
    1.08
    多少
    1.07
     зрения
    1.06
    டைய
    1.06
    önes
    1.05
    àng
    1.03
    
    1.03
    Activations Density 0.000%

    No Known Activations