© 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. 40-GEMMASCOPE-2-RES-262K
    7. 169876
    Prev
    Next
    INDEX
    Explanations

    pigeonhole principle and pigeons

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    やま
    0.38
     स्वरों
    0.38
    Boundary
    0.37
    ához
    0.36
     อุ
    0.36
    🎵
    0.36
    ʼn
    0.36
    ξύ
    0.35
    boundary
    0.35
     হাইড্র
    0.35
    POSITIVE LOGITS
     pigeon
    1.43
     pigeons
    1.30
     Pigeon
    1.24
    鴿
    1.13
    鸽
    1.09
    鳩
    0.81
    dove
    0.77
    igeon
    0.76
    igeons
    0.75
     dove
    0.73
    Activations Density 0.007%

    No Known Activations