© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130226
    Prev
    Next
    INDEX
    Explanations

    The neuron flags multi‐digit numeric tokens (e.g. phone numbers, addresses, or other long digit sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    phone numbers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     comté
    -1.16
     Hvor
    -1.10
     vẫn
    -1.05
     توص
    -1.04
    still
    -1.03
    为什么会
    -1.02
     spieg
    -1.02
     größte
    -1.00
    WireFormatLite
    -1.00
    شنبه
    -0.98
    POSITIVE LOGITS
     at
    1.25
     (
    1.24
     directly
    1.23
    וּ
    1.23
    ־ה
    1.05
     specifically
    1.03
    eloma
    1.03
     information
    1.02
     data
    0.96
     immediately
    0.95
    Activations Density 0.005%

    No Known Activations