© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8956
    Prev
    Next
    INDEX
    Explanations

    code syntax or structure

    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
    quoi
    2.37
    了一
    2.36
    了一個
    2.23
    了一个
    2.13
     k
    1.95
    了一些
    1.88
     bathe
    1.86
    了一种
    1.83
     luxe
    1.79
    了一条
    1.73
    POSITIVE LOGITS
    ي
    4.22
    ت
    4.10
    i
    4.08
    이
    4.05
    as
    4.03
    ת
    3.95
    k
    3.90
    ه
    3.86
    ০
    3.74
    es
    3.68
    Activations Density 2.628%

    No Known Activations