© 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. 34-GEMMASCOPE-RES-131K
    7. 63521
    Prev
    Next
    INDEX
    Explanations

    links to questions and answers

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

    This neuron detects references to Stack Exchange network question URLs (e.g. domain names like “stackoverflow.com” or “math.stackexchange.com” and their question‐ID paths).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Grü
    -0.85
     respira
    -0.81
     exposure
    -0.78
    chman
    -0.76
     acad
    -0.74
    ваясь
    -0.71
     dbName
    -0.71
     indifer
    -0.71
     acel
    -0.70
    WEBPACK
    -0.69
    POSITIVE LOGITS
     SOD
    0.80
    diğim
    0.80
    日本では
    0.78
    トヨタ
    0.78
     aján
    0.77
     photoshop
    0.76
     sutures
    0.75
    lamos
    0.75
    Jorge
    0.73
     nära
    0.73
    Activations Density 0.010%

    No Known Activations