© 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. 99113
    Prev
    Next
    INDEX
    Explanations

    Mississippi State, Justice, Case

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

    The neuron fires on numeric sports‐record and score patterns—especially win–loss or game statistics written as numbers (often in parentheses) separated by hyphens and commas.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    時的
    -0.83
    軟
    -0.73
     Uttarakhand
    -0.73
    同學
    -0.70
    فق
    -0.70
     भाव
    -0.69
     Kalimantan
    -0.69
    拋
    -0.69
     miejsco
    -0.69
     nổi
    -0.69
    POSITIVE LOGITS
     Dion
    0.78
     Anglo
    0.77
     Claudio
    0.76
     mã
    0.76
     Cyclo
    0.75
     Cougars
    0.74
     Pullman
    0.74
     código
    0.73
     drywall
    0.73
     BYU
    0.72
    Activations Density 0.029%

    No Known Activations