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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 97907
    Prev
    Next
    INDEX
    Explanations

    chicken and poultry

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

    references to poultry, especially chickens and related terms like "feathering" or "avian".

    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
     whale
    -1.03
     whales
    -1.03
     dolphins
    -0.98
     moose
    -0.95
     elephants
    -0.90
    whale
    -0.85
    鲸
    -0.85
     deer
    -0.82
     bison
    -0.81
    whal
    -0.81
    POSITIVE LOGITS
     chicken
    4.03
    chicken
    3.41
    Chicken
    3.31
     poultry
    3.30
     Chicken
    3.27
     chickens
    3.22
     Poultry
    2.81
     Chickens
    2.64
     CHICKEN
    2.41
    鸡
    2.33
    Activations Density 0.161%

    No Known Activations