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. 7947
    Prev
    Next
    INDEX
    Explanations

    United Arab Emirates

    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
     компьютера
    2.30
    plt
    2.08
    কে
    2.01
     daya
    1.99
     partid
    1.97
    ~/
    1.96
     بنت
    1.92
    तील
    1.92
    ında
    1.91
     श्रीमती
    1.87
    POSITIVE LOGITS
    ে
    2.08
    يج
    2.04
    <bos>
    1.92
    ೭
    1.91
    u
    1.91
    nY
    1.90
    isnan
    1.89
    鹉
    1.89
    tive
    1.88
    feel
    1.87
    Activations Density 0.001%

    No Known Activations