© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57290
    Prev
    Next
    INDEX
    Explanations

    ruminant and rumen function

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

    This neuron activates for content related to ruminant animals and rumen biology, particularly scientific text about digestion, metabolism, and feed studies in cattle or similar animals.

    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
    ธ์
    -0.81
    ͒
    -0.78
     pohod
    -0.76
    andom
    -0.75
     Month
    -0.73
     tôm
    -0.72
    wortet
    -0.72
     garis
    -0.71
    Coul
    -0.70
     Yamaguchi
    -0.70
    POSITIVE LOGITS
     rum
    1.35
     rumen
    1.30
    瘤
    1.10
     degradability
    0.96
    Rum
    0.94
     rumin
    0.94
     Rum
    0.91
    RUM
    0.88
     degrad
    0.87
    rum
    0.85
    Activations Density 0.053%

    No Known Activations