© 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. 34-GEMMASCOPE-RES-131K
    7. 99249
    Prev
    Next
    INDEX
    Explanations

    congenital

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

    The neuron activates for words beginning with "Cong" such as "Congenital" and "Congressional," especially in medical and organizational contexts.

    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
     bump
    -0.80
     ſtate
    -0.80
    bump
    -0.79
     ko
    -0.79
    ریب
    -0.75
    鸾
    -0.73
     ross
    -0.72
    iore
    -0.71
     kli
    -0.70
     ſtre
    -0.69
    POSITIVE LOGITS
     Cong
    1.74
    Cong
    1.72
     conges
    1.21
     cong
    1.18
    cong
    1.17
     congreg
    1.05
     congre
    1.02
     congru
    0.94
     Congregation
    0.88
     congressional
    0.87
    Activations Density 0.016%

    No Known Activations