© 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. 174378
    Prev
    Next
    INDEX
    Explanations

    anatomy and anatomy

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

    adjusting values

    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
    于是
    0.52
     edged
    0.45
     |
    0.45
    到
    0.44
    轴
    0.44
    到底
    0.44
    后续
    0.43
    不
    0.43
    重要
    0.43
    发射
    0.43
    POSITIVE LOGITS
    <unused94>
    0.58
    casters
    0.57
    bles
    0.52
     Zim
    0.49
    <unused998>
    0.49
     Zambia
    0.48
     Zuma
    0.47
     অ্যাপ
    0.46
     Kas
    0.45
     Amar
    0.45
    Activations Density 0.001%

    No Known Activations