© 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. 22-GEMMASCOPE-RES-131K
    7. 73503
    Prev
    Next
    INDEX
    Explanations

    phone numbers

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

    This neuron detects digit characters (particularly in phone‐number or other hyphenated numeric sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     these
    -1.23
     verschill
    -1.21
    It
    -1.07
     früheren
    -1.06
     bekannten
    -1.05
     größten
    -0.99
    Ｊ
    -0.96
    เป็น
    -0.95
     ähnlichen
    -0.95
     traditionellen
    -0.94
    POSITIVE LOGITS
     Zeug
    1.06
     Francus
    1.05
    Shame
    1.05
     první
    1.05
     seier
    1.03
    ＄
    0.96
    ████
    0.96
    🆅
    0.94
     tirada
    0.93
    вича
    0.93
    Activations Density 0.002%

    No Known Activations