© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34833
    Prev
    Next
    INDEX
    Explanations

    phone numbers

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

    The neuron strongly activates on long contiguous digit sequences typical of phone numbers.

    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
    جمع
    -1.06
    ɴ
    -1.00
    ňte
    -0.92
     גם
    -0.90
     אל
    -0.89
    roppo
    -0.88
    cloth
    -0.88
    Де
    -0.87
    mètre
    -0.85
     vaisselle
    -0.85
    POSITIVE LOGITS
    Boxscore
    0.91
     go
    0.90
    얻
    0.88
     DÍA
    0.88
     Ebenso
    0.86
    Cześć
    0.85
     этих
    0.85
     llamada
    0.84
    Symmetry
    0.83
     llamado
    0.82
    Activations Density 0.005%

    No Known Activations