© 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. 20833
    Prev
    Next
    INDEX
    Explanations

    expiration dates and timelines

    np_acts-logits-general · gemini-2.5-flash-lite

    Contact Information

    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
    č
    0.43
    íp
    0.41
    ¡
    0.41
    ú
    0.41
    bits
    0.40
    min
    0.39
    spring
    0.39
    я
    0.39
     reluctantly
    0.39
    Ка
    0.39
    POSITIVE LOGITS
     comparaison
    0.54
     آدمی
    0.50
     নির্দিষ্ট
    0.50
     এমনই
    0.49
    이면
    0.49
     بهترین
    0.49
     ανθρώ
    0.49
     συγκεκρι
    0.48
     fonctionnent
    0.48
     查询
    0.47
    Activations Density 0.000%

    No Known Activations