© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5067
    Prev
    Next
    INDEX
    Explanations

    domestic violence hotline numbers

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

    This neuron detects numerical tokens or number sequences, such as parts of phone numbers and numeric addresses.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    hte
    0.57
    this
    0.56
    沢山
    0.54
    diction
    0.54
    에서는
    0.53
    IQR
    0.53
    Quaternion
    0.52
    э
    0.52
    This
    0.52
    identity
    0.52
    POSITIVE LOGITS
     knapp
    0.65
    ysseus
    0.61
     hopp
    0.60
     HELP
    0.59
     hola
    0.59
     dokter
    0.57
     tenis
    0.57
    
    0.57
     tl
    0.57
     nadzie
    0.57
    Activations Density 0.043%

    No Known Activations