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. 7406
    Prev
    Next
    INDEX
    Explanations

    accomplishment

    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
    氖
    1.41
    𝑤
    1.37
     Prakash
    1.33
    𝗴
    1.30
    nDims
    1.29
     barbec
    1.29
     disgr
    1.29
    🩶
    1.29
    cmath
    1.28
    ল
    1.27
    POSITIVE LOGITS
    ัพท์
    1.29
    t
    1.11
    хід
    1.11
    ोक
    1.11
    inde
    1.09
    ï
    1.09
     وين
    1.05
    нім
    1.04
     affords
    1.03
    ंजक
    1.00
    Activations Density 0.000%

    No Known Activations