© 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. 64204
    Prev
    Next
    INDEX
    Explanations

    phone numbers and postal codes

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

    The neuron fires on individual digits that appear as part of longer numeric sequences (e.g. phone numbers or other multi-digit strings).

    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
     that
    -1.20
    AutoScaleMode
    -0.91
     fomentar
    -0.90
    できなかった
    -0.90
    staticmethod
    -0.89
    مانی
    -0.87
     Slovensku
    -0.86
    guet
    -0.85
     podjet
    -0.84
    There
    -0.83
    POSITIVE LOGITS
     %\
    0.96
     jeunes
    0.85
    Deacti
    0.80
     discu
    0.79
    軽量
    0.78
     nimble
    0.77
    LEVANT
    0.76
    回転
    0.75
     ощу
    0.75
     origine
    0.75
    Activations Density 0.004%

    No Known Activations