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. 47163
    Prev
    Next
    INDEX
    Explanations

    healthcare.gov

    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
     מק
    1.31
    㙅
    1.27
     pédicule
    1.26
     vermutlich
    1.26
     celé
    1.25
     suffit
    1.21
     supplémentaires
    1.19
    osť
    1.19
    \}-
    1.18
     bcrypt
    1.18
    POSITIVE LOGITS
    1
    1.03
    शन
    0.94
     gew
    0.91
    cul
    0.90
    creto
    0.89
    ar
    0.88
    q
    0.87
    neg
    0.87
     hel
    0.85
    at
    0.85
    Activations Density 0.003%

    No Known Activations