© 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. 72421
    Prev
    Next
    INDEX
    Explanations

    numbers preceding words

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

    acknowledges or work

    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
    人文
    0.54
    한
    0.53
    霸
    0.50
    엔
    0.48
    스트
    0.47
    문
    0.47
     tecnológico
    0.47
    德
    0.47
    文
    0.46
    鏈
    0.46
    POSITIVE LOGITS
     For
    0.48
     Mount
    0.48
     ব্যাপারে
    0.47
     arose
    0.47
     Leopard
    0.46
     Floating
    0.45
     Glove
    0.45
     Command
    0.43
     Comando
    0.43
     Roof
    0.43
    Activations Density 0.001%

    No Known Activations