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

    Neuronpedia

    Jacobian LensNEW
    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. 9997
    Prev
    Next
    INDEX
    Explanations

    physical science journals and computing

    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
    ン
    1.67
     um
    1.65
    יא
    1.58
     giraffe
    1.50
     ao
    1.49
    ايا
    1.49
    RY
    1.49
     inconsistency
    1.46
    ाना
    1.45
    াতাড়ি
    1.45
    POSITIVE LOGITS
    т
    1.44
     Jewelry
    1.42
    coords
    1.35
     Scientific
    1.33
    器件
    1.33
     ಮೀ
    1.30
     Başkan
    1.29
    ckpt
    1.26
     बिहारी
    1.26
    с
    1.25
    Activations Density 0.004%

    No Known Activations