© 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. 8925
    Prev
    Next
    INDEX
    Explanations

    stay instructions

    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
    ات
    3.10
    ात
    2.95
    পরে
    2.91
    sz
    2.88
    ম
    2.88
    িন
    2.87
    انية
    2.81
    ération
    2.80
    ා
    2.78
    s
    2.72
    POSITIVE LOGITS
    のは
    3.62
    ので
    3.23
     yerden
    3.13
     afloat
    3.13
     πως
    2.91
    ся
    2.88
     μην
    2.72
    ছিলেন
    2.61
    Bibliografia
    2.56
    evsky
    2.55
    Activations Density 0.029%

    No Known Activations