© 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. 15475
    Prev
    Next
    INDEX
    Explanations

    gmail email addresses

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

    The neuron fires specifically on occurrences of “gmail” in email addresses.

    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
     "
    -1.34
     on
    -1.28
    laven
    -1.20
     that
    -1.20
    EEE
    -1.20
     همچنین
    -1.18
    !!!!!!!
    -1.16
    ...........
    -1.14
    OE
    -1.13
    through
    -1.12
    POSITIVE LOGITS
    Gmail
    1.37
    Reak
    1.21
    موقع
    1.19
    Nieuwe
    1.17
    Mua
    1.12
    閖
    1.09
     entraîner
    1.09
     reager
    1.04
     vétérina
    1.04
     écl
    1.03
    Activations Density 0.005%

    No Known Activations