© 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. 158932
    Prev
    Next
    INDEX
    Explanations

    parent or guardian

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

    words like found

    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
    访问
    0.49
    学习
    0.47
    宣
    0.46
    ป็น
    0.44
    лан
    0.43
     हूँ
    0.43
    宝
    0.43
    搵
    0.43
    从事
    0.42
    Wikipedia
    0.42
    POSITIVE LOGITS
     épaules
    0.52
     bintang
    0.49
     empêcher
    0.48
     шести
    0.46
     großen
    0.46
    utada
    0.46
     Sabah
    0.46
     suiv
    0.46
     albo
    0.45
     chests
    0.44
    Activations Density 0.001%

    No Known Activations