© 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. 10-GEMMASCOPE-RES-131K
    7. 14667
    Prev
    Next
    INDEX
    Explanations

    web sites and pages

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

    This neuron detects the token “Web” (in headings, URLs, class names, etc.).

    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
    </h2>
    -1.77
    </h6>
    -1.66
    ’
    -1.66
    狨
    -1.63
     complicada
    -1.58
    籥
    -1.50
     dú
    -1.48
     alſo
    -1.48
    шают
    -1.47
    嫆
    -1.46
    POSITIVE LOGITS
    ā
    2.08
     oferty
    1.82
     thượng
    1.72
     eventual
    1.59
     originaux
    1.59
    ch
    1.59
    女兒
    1.56
     پنجم
    1.55
     literal
    1.52
     paznok
    1.51
    Activations Density 0.035%

    No Known Activations