© 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. 11767
    Prev
    Next
    INDEX
    Explanations

    1, sequence starter

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

    code, python, or foreign language

    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
     добавить
    0.43
    ྕ
    0.42
    drawString
    0.42
    嗲
    0.40
    递
    0.40
    ̬
    0.40
    栈
    0.38
     图片
    0.38
    变量
    0.38
     যাওয়ার
    0.37
    POSITIVE LOGITS
     totalidad
    0.45
     auch
    0.44
     meus
    0.44
     nimi
    0.43
     inescap
    0.43
     endet
    0.43
     unseres
    0.42
     meinen
    0.42
     celle
    0.42
     benim
    0.42
    Activations Density 0.002%

    No Known Activations