© 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. 32207
    Prev
    Next
    INDEX
    Explanations

    phone numbers and contact information

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

    The neuron activates on long sequences of digits, specifically phone‐number or contact‐info numeric tokens.

    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
     on
    -1.08
     a
    -1.06
    startY
    -0.97
    љу
    -0.95
    WORDS
    -0.91
     s
    -0.90
     недостатки
    -0.90
     first
    -0.89
    A
    -0.89
    ｐ
    -0.89
    POSITIVE LOGITS
    RESTAUR
    1.05
    sandalias
    1.02
    spare
    1.02
    busca
    1.02
    zapatillas
    1.00
     réve
    1.00
     телефону
    0.99
     WhatsApp
    0.99
     accompagner
    0.99
     coû
    0.98
    Activations Density 0.011%

    No Known Activations