© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62363
    Prev
    Next
    INDEX
    Explanations

    sigma-1, sigma-70, sigma receptor

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

    The neuron detects the Greek letter "sigma" and related scientific notations, particularly in biochemistry and mathematical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    invent
    -0.73
     salga
    -0.71
     implicit
    -0.70
    
    -0.69
     rodillas
    -0.68
    serving
    -0.67
    inaire
    -0.66
    幼
    -0.66
     ejemplo
    -0.66
    authier
    -0.66
    POSITIVE LOGITS
    Sigma
    0.94
    σ
    0.92
     Sigma
    0.92
     }}{
    0.77
     veck
    0.77
    
    0.77
     Sig
    0.76
    sigma
    0.75
    SIGMA
    0.75
    kirk
    0.75
    Activations Density 0.016%

    No Known Activations