© 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. 10-GEMMASCOPE-RES-131K
    7. 74336
    Prev
    Next
    INDEX
    Explanations

    visit our page/website

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

    The neuron activates on call-to-action phrases that direct readers to “visit” or “contact” a website or page (e.g. “visit us at…,” “please visit our…”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    참고
    -1.42
     vayas
    -1.30
     laquelle
    -1.29
     lesquels
    -1.23
     their
    -1.20
     a
    -1.20
     behö
    -1.20
     informée
    -1.20
    Beskrivning
    -1.18
     wcześniej
    -1.16
    POSITIVE LOGITS
     at
    1.93
    ’
    1.83
     in
    1.57
    อีก
    1.42
     But
    1.42
    нибудь
    1.34
     otros
    1.31
     registrados
    1.30
     until
    1.29
    textColor
    1.28
    Activations Density 0.021%

    No Known Activations