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. 9-GEMMASCOPE-2-RES-262K
    4. 7521
    Prev
    Next
    INDEX
    Explanations

    one-to-one relationships

    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
    मान
    1.30
    تين
    1.28
    lop
    1.22
     zda
    1.21
    ت
    1.12
    tart
    1.11
    Além
    1.11
    midt
    1.09
    tod
    1.08
     Aik
    1.08
    POSITIVE LOGITS
     foram
    1.27
     mieli
    1.25
    ಿಸಲ
    1.22
    ధీ
    1.22
     kiş
    1.20
    hours
    1.19
    ১
    1.19
     bulunan
    1.18
    បាន
    1.17
    𝐎
    1.17
    Activations Density 0.000%

    No Known Activations