© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 69838
    Prev
    Next
    INDEX
    Explanations

    legal information and services

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

    This neuron responds to phone numbers and call-to-action contact info (e.g. “Call us,” free consultation, and digit strings for dialing).

    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
    הס
    -0.77
     gă
    -0.76
    كس
    -0.75
     Stornier
    -0.75
     Prerequisite
    -0.73
    middels
    -0.73
     feminino
    -0.73
    廈
    -0.72
     asistir
    -0.72
    Negocio
    -0.71
    POSITIVE LOGITS
    lawyer
    0.90
    appointment
    0.86
    Case
    0.85
     urgente
    0.85
     %).
    0.84
     attorney
    0.82
     confidential
    0.82
     intake
    0.82
     Case
    0.81
    VK
    0.79
    Activations Density 0.010%

    No Known Activations