© 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. 9542
    Prev
    Next
    INDEX
    Explanations

    non-english programming constructs

    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
     নিষ্পত্তি
    0.82
    y
    0.81
    sourceforge
    0.80
     surjective
    0.80
    o
    0.80
    oč
    0.79
    ações
    0.77
     सत्तार
    0.77
    ে
    0.76
     hydrochloride
    0.76
    POSITIVE LOGITS
    ள்
    0.89
    ال
    0.83
    ల
    0.82
     लिए
    0.82
    0.79
    ==========
    0.77
    ПО
    0.77
    <0x80>
    0.76
     г
    0.75
    igo
    0.73
    Activations Density 0.140%

    No Known Activations