© 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. 111864
    Prev
    Next
    INDEX
    Explanations

    human biology and states

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

    The neuron activates on the word "human," particularly when referring to humans as a species or to human physiology.

    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_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
     leaſt
    -2.03
     plupart
    -1.89
    ."
    -1.82
     Perspek
    -1.73
     sebuah
    -1.61
     alcuni
    -1.61
     vielen
    -1.60
    ates
    -1.55
    зраст
    -1.53
     ͜ʖ
    -1.53
    POSITIVE LOGITS
    {
    1.63
     beings
    1.61
    
    1.61
    怿
    1.61
     最後
    1.55
    Ꮟ
    1.55
    酝
    1.54
    Église
    1.53
     setUsername
    1.52
    ッソ
    1.51
    Activations Density 0.072%

    No Known Activations