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. 47212
    Prev
    Next
    INDEX
    Explanations

    resident ID card

    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
    an
    1.12
    र
    1.06
    ോട്ട
    1.06
     incentives
    1.04
     kung
    1.03
    ከል
    1.02
    র
    1.01
    ν
    0.99
    incent
    0.99
     incentive
    0.98
    POSITIVE LOGITS
    jsonify
    1.25
     liable
    1.24
    HasStarred
    1.18
     그래서
    1.13
    boundingBox
    1.11
     amy
    1.10
    িত্ব
    1.08
    폰
    1.06
     jsonify
    1.05
     특
    1.05
    Activations Density 0.002%

    No Known Activations