© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106164
    Prev
    Next
    INDEX
    Explanations

    email addresses, protected

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

    The neuron is detecting email‐address tokens and related “protected”/“hidden” email placeholders.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    дзі
    -0.77
    த்தை
    -0.72
     sobą
    -0.69
     فار
    -0.68
    monds
    -0.67
     cinematogra
    -0.65
     空
    -0.64
    Curves
    -0.63
     adatok
    -0.62
    南海
    -0.62
    POSITIVE LOGITS
    zz
    0.69
     protected
    0.69
     psychoanalysis
    0.68
     sheltered
    0.68
     knotted
    0.67
     мем
    0.66
    郜
    0.65
    Fiat
    0.65
    iras
    0.65
    protected
    0.65
    Activations Density 0.039%

    No Known Activations