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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7535
    Prev
    Next
    INDEX
    Explanations

    is / is a / is on / is a tomato / is arguably

    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
    াহারের
    1.35
    skins
    1.32
    త్య
    1.25
    𝚛
    1.21
    ל
    1.20
    ற்புத
    1.19
    ళ్లి
    1.18
    $.
    1.17
     needles
    1.17
    弛
    1.16
    POSITIVE LOGITS
     इसीलिए
    1.29
    d
    1.19
    pecific
    1.16
    𝙔
    1.15
    Ле
    1.15
    dQ
    1.12
    isHorizontal
    1.12
     uplifting
    1.12
    ри
    1.10
    𝘼
    1.08
    Activations Density 0.000%

    No Known Activations