© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205822
    Prev
    Next
    INDEX
    Explanations

    ambiguous and non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    They
    0.48
    As
    0.45
    valores
    0.45
    No
    0.42
    ক্তিক
    0.42
    By
    0.42
     प्यारे
    0.42
    He
    0.41
    Ǘ
    0.41
    Environmental
    0.40
    POSITIVE LOGITS
     chiều
    0.59
     بهبود
    0.54
     několik
    0.49
     bóng
    0.49
     độ
    0.48
    ações
    0.48
     ambiguity
    0.48
     ဝ
    0.48
    
    0.47
     ambiguous
    0.47
    Activations Density 0.001%

    No Known Activations