© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99494
    Prev
    Next
    INDEX
    Explanations

    chicken breeds and yeast

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

    mentions of birds, specifically chickens and poultry-related terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Witkin
    -0.84
    mila
    -0.82
    🐊
    -0.75
    医師
    -0.75
     файла
    -0.73
    nikami
    -0.73
     кабель
    -0.73
     Promotions
    -0.73
    fung
    -0.72
     شیر
    -0.71
    POSITIVE LOGITS
     backyard
    1.05
     laying
    0.97
     hens
    0.94
     hen
    0.85
    dymyr
    0.84
    Kü
    0.82
    cinq
    0.82
    Gön
    0.81
     Craigslist
    0.80
     probiotics
    0.80
    Activations Density 0.017%

    No Known Activations