© 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. 173918
    Prev
    Next
    INDEX
    Explanations

    Nuclear family background

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

    trying to mitigate or include

    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
    一对
    0.46
    圆形
    0.44
    紧
    0.44
     register
    0.43
     CNRS
    0.43
    ায়ণ
    0.43
     Register
    0.43
    !;
    0.42
    送到
    0.42
    适当
    0.42
    POSITIVE LOGITS
     detergents
    0.48
     provides
    0.47
    rational
    0.46
     سا
    0.45
     مضر
    0.45
     Provides
    0.43
    rata
    0.42
    mineral
    0.42
    OPLE
    0.42
     harmful
    0.42
    Activations Density 0.002%

    No Known Activations