© 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. 92809
    Prev
    Next
    INDEX
    Explanations

    court cases and arguments

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

    This neuron strongly activates on numeric characters or sequences (digits), i.e., it detects numbers.

    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
    Those
    -0.82
     brevis
    -0.79
     first
    -0.77
     européennes
    -0.75
     Mathematik
    -0.74
     steadily
    -0.73
     Those
    -0.71
    éns
    -0.71
     रहा
    -0.70
     In
    -0.70
    POSITIVE LOGITS
     conference
    0.90
    casecmp
    0.84
    
    0.83
     DEFENSE
    0.80
    cussions
    0.79
    timacy
    0.79
    reel
    0.76
     刺繍
    0.76
     FEE
    0.75
     identifiés
    0.75
    Activations Density 0.001%

    No Known Activations