© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8521
    Prev
    Next
    INDEX
    Explanations

    bird or birds

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

    bird and birds

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     porcine
    0.49
    🦍
    0.48
     gorilla
    0.47
    cambrian
    0.47
    🐷
    0.47
    animals
    0.46
    🦈
    0.46
     microorganism
    0.46
    蜈
    0.46
    🐖
    0.46
    POSITIVE LOGITS
     bird
    1.46
     Bird
    1.35
    Bird
    1.28
     birds
    1.23
     Birds
    1.17
    鳥
    1.14
    bird
    1.13
    鸟
    1.09
    🐦
    1.02
     пти
    1.01
    Activations Density 0.227%

    No Known Activations