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. 7464
    Prev
    Next
    INDEX
    Explanations

    Subject:

    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
    på
    2.61
    পন্থ
    2.31
    и
    2.29
     receptive
    2.24
    情况下
    2.19
    ینک
    2.17
    事情
    2.13
    weist
    2.12
    තුර
    2.12
     geç
    2.12
    POSITIVE LOGITS
    ה
    2.91
    σει
    2.42
    ும்
    2.30
    скія
    2.19
    आती
    2.18
    щая
    2.12
     localObject
    2.10
    ी
    2.06
    uret
    2.02
    वस्तु
    1.99
    Activations Density 0.178%

    No Known Activations