© 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. 22-GEMMASCOPE-RES-131K
    7. 25390
    Prev
    Next
    INDEX
    Explanations

    phone numbers and contact info

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

    The neuron fires on long sequences of digits and related punctuation (e.g. phone‐number–style numeric strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     community
    -1.41
     people
    -1.30
     this
    -1.29
     all
    -1.25
     children
    -1.14
     suggests
    -1.13
     residents
    -1.11
     school
    -1.10
     four
    -1.09
     getting
    -1.09
    POSITIVE LOGITS
    亟
    1.54
     Eſ
    1.34
    诟
    1.30
    欤
    1.29
     testar
    1.29
     explicou
    1.26
     wilfully
    1.26
    一时间
    1.26
    歟
    1.26
     pory
    1.25
    Activations Density 0.009%

    No Known Activations