© 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. 10-GEMMASCOPE-RES-131K
    7. 10905
    Prev
    Next
    INDEX
    Explanations

    chicken

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

    This neuron activates on mentions of poultry (especially the word “chicken”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    栳
    -2.83
    u
    -2.75
    *
    -2.72
     gerçekten
    -2.55
    籥
    -2.52
    .........
    -2.41
    作品の
    -2.38
    真的是
    -2.38
    但我
    -2.33
     But
    -2.31
    POSITIVE LOGITS
    ization
    3.56
    溦
    3.11
    蟜
    3.06
     男士
    2.97
    蛩
    2.86
     帅气
    2.86
    ");
    2.86
    脔
    2.84
     titel
    2.77
    𐑂
    2.75
    Activations Density 0.004%

    No Known Activations