© 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. 128073
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on occurrences of the word “browser” (and its morphological variants like “browsers,” “BrowserName,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    browser name and version

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     you
    -2.47
    ?"
    -2.36
     It
    -2.30
    泐
    -2.20
     kostet
    -2.03
     benef
    -2.02
    付いて
    -2.00
     identifiés
    -1.99
    </em>
    -1.98
    并未
    -1.95
    POSITIVE LOGITS
    3
    2.44
    9
    2.31
    狆
    2.14
    🢐
    1.99
     wszyst
    1.96
     事業
    1.95
     eigenes
    1.94
     combinations
    1.90
    <i>
    1.89
     gemeins
    1.87
    Activations Density 0.013%

    No Known Activations