© 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. 116185
    Prev
    Next
    INDEX
    Explanations

    legislation and government questions

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

    The neuron is triggered by numeric tokens (sequences of digits) embedded in the text.

    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
    kant
    -0.79
     NOAA
    -0.77
    fileprivate
    -0.75
     Kors
    -0.74
     航空
    -0.72
    ificação
    -0.71
    塵
    -0.71
     trusty
    -0.70
     severance
    -0.70
     Manganese
    -0.68
    POSITIVE LOGITS
     Governor
    0.91
    Governor
    0.85
     Trailer
    0.84
     Niveau
    0.80
    geek
    0.79
    dorf
    0.77
    enscha
    0.75
    Trailer
    0.75
     constitutional
    0.75
     scuola
    0.75
    Activations Density 0.006%

    No Known Activations