Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7323
    Prev
    Next
    INDEX
    Explanations

    code snippets and structured text

    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_9_width_262k_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
    te
    1.39
    ுங்கள்
    1.34
    ी
    1.26
    ⣿
    1.26
    வே
    1.25
    e
    1.19
    mehr
    1.19
    り
    1.19
    те
    1.18
     tập
    1.16
    POSITIVE LOGITS
     Disabilities
    1.48
    ط
    1.41
     Jdbc
    1.32
    𝐩
    1.29
     notions
    1.29
     documentación
    1.28
    েন্ট
    1.27
    墅
    1.27
    ів
    1.27
     sikap
    1.26
    Activations Density 0.000%

    No Known Activations