© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 240715
    Prev
    Next
    INDEX
    Explanations

    lists, pages, editions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neuron
    0.50
    體的
    0.48
     শি
    0.47
    filters
    0.47
    some
    0.46
    graphicx
    0.46
    ä
    0.46
    uuid
    0.46
    refundable
    0.45
    undet
    0.45
    POSITIVE LOGITS
    竑
    0.48
     be
    0.45
     оста
    0.44
    ২৫
    0.44
     диви
    0.44
    евич
    0.43
     einzigen
    0.43
    Homepage
    0.43
    엡
    0.43
     microcos
    0.42
    Activations Density 0.000%

    No Known Activations