© 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. 10-GEMMASCOPE-RES-131K
    7. 130910
    Prev
    Next
    INDEX
    Explanations

    contact for contact information

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

    The neuron specializes in spotting “contact” information lines, especially those listing 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_10/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
     они
    -1.82
    が高
    -1.73
    なども
    -1.69
    These
    -1.69
    螄
    -1.67
    🪤
    -1.63
    蹰
    -1.63
     économie
    -1.62
     fazia
    -1.59
     român
    -1.57
    POSITIVE LOGITS
     our
    2.34
     by
    1.90
     or
    1.83
     serdecznie
    1.80
     as
    1.79
     one
    1.71
    {
    1.67
     their
    1.66
     doskon
    1.66
    <em>
    1.64
    Activations Density 0.007%

    No Known Activations