© 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. 22-GEMMASCOPE-RES-131K
    7. 75180
    Prev
    Next
    INDEX
    Explanations

    phone numbers or contact details

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

    The neuron activates on multi‐digit numeric sequences (e.g. phone numbers, addresses, or other long digit 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
     also
    -1.21
     even
    -1.11
     l
    -1.05
     растений
    -1.05
    ickle
    -1.03
    겼
    -1.03
     we
    -1.01
     Voraussetzung
    -0.98
     enth
    -0.95
    ｃ
    -0.95
    POSITIVE LOGITS
    ּוֹ
    1.62
    ଵ
    1.45
    ଶ
    1.42
    giày
    1.35
     یا
    1.30
    וּ
    1.27
     бампер
    1.27
    Жит
    1.24
     Drittan
    1.24
    tambah
    1.23
    Activations Density 0.010%

    No Known Activations