© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13069
    Prev
    Next
    INDEX
    Explanations

    contact information and calls to action

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

    The neuron identifies contact and logistical details such as phone numbers, email addresses, URLs, and other “for more information”/event details.

    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
     rajut
    -2.13
     rokok
    -1.90
     rése
    -1.80
     diki
    -1.79
     tunik
    -1.78
     dekol
    -1.77
     torba
    -1.76
     remercier
    -1.74
     malheureux
    -1.71
     thoſe
    -1.69
    POSITIVE LOGITS
     to
    3.19
     on
    2.75
     at
    2.73
     of
    2.45
     from
    2.44
     only
    2.41
     into
    2.34
     as
    2.20
     but
    2.20
     after
    2.09
    Activations Density 0.019%

    No Known Activations