© 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. 173343
    Prev
    Next
    INDEX
    Explanations

    common Chinese phrases

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

    prejudice and sensitive topics

    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
     bursts
    0.52
     vigorously
    0.50
     queued
    0.49
     Israelis
    0.49
     passively
    0.49
    ^*
    0.49
     partially
    0.47
     APO
    0.47
    oxych
    0.47
    fourths
    0.46
    POSITIVE LOGITS
    Чер
    0.49
    阊
    0.48
    常见
    0.47
    准备
    0.47
    人和
    0.47
    分钟
    0.47
    ę
    0.46
    编写
    0.46
    华
    0.46
    შინ
    0.46
    Activations Density 0.001%

    No Known Activations