© 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. 166758
    Prev
    Next
    INDEX
    Explanations

    reminder of

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

    **American** or **I was**

    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
     کنید
    0.53
    гает
    0.45
    လျှ
    0.45
    า
    0.44
     என்க
    0.43
     በተጨማሪ
    0.43
     minimizes
    0.42
     ማለት
    0.42
     আকৃষ্ট
    0.42
     матрицы
    0.42
    POSITIVE LOGITS
    呋
    0.46
     Ud
    0.44
     Yoshida
    0.44
     Tomas
    0.44
    細菌
    0.44
     aromatic
    0.44
    Overwrite
    0.43
    orden
    0.43
     Resolve
    0.43
    ormal
    0.43
    Activations Density 0.000%

    No Known Activations