© 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. 71035
    Prev
    Next
    INDEX
    Explanations

    Choose a

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

    United States of America, government

    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
     meravigli
    0.50
    ITIS
    0.50
     المغ
    0.50
    zy
    0.48
     magní
    0.47
    悉
    0.47
     positifs
    0.47
     positif
    0.47
    چا
    0.46
     olduğu
    0.46
    POSITIVE LOGITS
    〠
    0.43
    ্না
    0.41
     أحد
    0.40
     worsening
    0.40
     Betty
    0.39
     Patty
    0.39
    萝
    0.39
     লক্ষ
    0.39
     toning
    0.39
    の一
    0.39
    Activations Density 0.000%

    No Known Activations