© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 119793
    Prev
    Next
    INDEX
    Explanations

    low-carb diet

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

    specifically explains how something presents

    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
    Negative Logits
    اء
    0.54
    είτε
    0.46
    ліся
    0.45
    赐
    0.45
    وريا
    0.43
    øj
    0.43
    锗
    0.43
    ين
    0.42
    在了
    0.42
    鶯
    0.42
    POSITIVE LOGITS
     kapsam
    0.55
     중
    0.47
    REGIUNE
    0.46
    ncol
    0.46
     ウェ
    0.46
     계
    0.45
     wcex
    0.45
    bala
    0.45
    ['
    0.44
     컨
    0.44
    Activations Density 0.000%

    No Known Activations