© 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. 30439
    Prev
    Next
    INDEX
    Explanations

    please contact

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

    This neuron detects numeric and commercial contact information—prices, phone numbers, order codes, and related digits.

    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
    Р
    -1.10
     kuah
    -1.07
     Terkait
    -1.07
    Obrigada
    -1.07
    Я
    -1.05
     Appetit
    -1.03
    ఏ
    -1.02
    Ї
    -1.00
    Į
    -1.00
     associée
    -1.00
    POSITIVE LOGITS
     contact
    2.02
     please
    1.56
    contact
    1.40
     hurry
    1.36
     WhatsApp
    1.33
     kindly
    1.33
    Contact
    1.30
    สนใจ
    1.30
     contacts
    1.27
     Contact
    1.25
    Activations Density 0.037%

    No Known Activations