© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57498
    Prev
    Next
    INDEX
    Explanations

    programming and scientific terms

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

    The neuron detects numeric tokens (sequences of digits).

    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
    usik
    -0.82
     сто
    -0.76
     social
    -0.70
    众多
    -0.68
     irrational
    -0.67
     risk
    -0.66
    issu
    -0.66
     от
    -0.66
     victims
    -0.65
    贴
    -0.63
    POSITIVE LOGITS
     ROS
    1.17
    ROS
    1.07
     Veterinary
    1.01
     rospy
    0.95
     veterinary
    0.89
    rost
    0.86
     gospod
    0.86
     veterinarians
    0.85
     ros
    0.85
     Statements
    0.84
    Activations Density 0.014%

    No Known Activations