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. 1935
    Prev
    Next
    INDEX
    Explanations

    python code syntax

    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
     vielfält
    1.00
     (§
    0.95
     §§
    0.91
    †
    0.87
     ecosystems
    0.87
    typically
    0.85
    ไตล์
    0.83
    partisan
    0.83
     résumé
    0.83
    Ō
    0.81
    POSITIVE LOGITS
    7
    1.19
    5
    1.12
    buton
    1.09
     সম্ভবনা
    1.08
    2
    1.07
    Catagory
    1.07
    里面
    1.06
    6
    1.05
    recieve
    1.05
    3
    1.04
    Activations Density 0.422%

    No Known Activations