© 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. 106597
    Prev
    Next
    INDEX
    Explanations

    Livermore, Dublin, Pleasanton

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

    This neuron detects numeric tokens (digits and numbers of any length) 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
    BBB
    -0.86
    bieter
    -0.78
    ANAL
    -0.77
    lüssel
    -0.77
     nyc
    -0.74
    ANIEL
    -0.73
     nhi
    -0.72
    ;",
    -0.70
    Soto
    -0.69
     zz
    -0.69
    POSITIVE LOGITS
     Livermore
    1.25
     Dublin
    1.09
    Dublin
    1.05
    Liver
    0.88
     Pleasant
    0.86
     liver
    0.80
    enquête
    0.79
     Danville
    0.79
     plă
    0.74
     Ireland
    0.70
    Activations Density 0.023%

    No Known Activations