© 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. 81131
    Prev
    Next
    INDEX
    Explanations

    how long

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

    common phrase beginnings

    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
    ឡិច
    0.50
     transformative
    0.49
     gennaio
    0.48
    ázej
    0.48
     refocus
    0.48
     keing
    0.48
    嗔
    0.47
    avion
    0.46
    ใจ
    0.45
     गेला
    0.45
    POSITIVE LOGITS
     牛
    0.53
    INTS
    0.46
     今日
    0.46
     техні
    0.45
    牷
    0.44
     ಸಾಮಾನ್ಯ
    0.44
    ")){
    0.44
    recv
    0.43
    nson
    0.43
     बिल्कुल
    0.43
    Activations Density 0.000%

    No Known Activations