© 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. 117132
    Prev
    Next
    INDEX
    Explanations

    legal, technical, and descriptive terms

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

    This neuron fires on isolated, capitalized or title‐style words used as section headings or labels (e.g. “Reviews,” “Accessibility,” “Topic,” “Version,” “Returns,” “Class,” “Overflow,” “Habitats,” “Inc.”, “Reserved”).

    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
     sores
    -0.76
     Rim
    -0.73
     Quora
    -0.73
     Moles
    -0.73
    httpRequest
    -0.70
     Diam
    -0.69
     Mouse
    -0.69
    霆
    -0.69
     LW
    -0.69
     rim
    -0.68
    POSITIVE LOGITS
    wyczaj
    0.81
     فوق
    0.77
    ͭ
    0.76
    tisation
    0.75
     groupName
    0.75
    furnished
    0.75
    صال
    0.72
    String
    0.72
     successivo
    0.72
     riuscito
    0.71
    Activations Density 0.023%

    No Known Activations