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. 1957
    Prev
    Next
    INDEX
    Explanations

    core, heart, or case

    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
     lui
    0.37
    ри
    0.36
    ⅼ
    0.35
     других
    0.34
     ті
    0.34
     другим
    0.33
    樟
    0.32
     అదే
    0.32
     площади
    0.32
     другими
    0.31
    POSITIVE LOGITS
    只要
    0.49
    jref
    0.49
    त्रेयी
    0.48
     மட்டுமே
    0.48
     이는
    0.46
    ♉
    0.45
     stemming
    0.45
    órias
    0.44
    ឹម
    0.43
     transcends
    0.43
    Activations Density 0.378%

    No Known Activations