© 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. 92729
    Prev
    Next
    INDEX
    Explanations

    website creation and building tools

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

    The neuron is keyed to discussions of building or hosting websites—i.e. mentions of web‐site, web‐hosting, site‐building services and related platform names.

    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
    下载
    -0.88
    发送
    -0.83
    た
    -0.81
     discussion
    -0.78
    aş
    -0.77
     napisał
    -0.76
    attore
    -0.76
    łucha
    -0.75
    ம
    -0.73
     session
    -0.73
    POSITIVE LOGITS
     templates
    1.73
     creation
    1.66
     creating
    1.66
     création
    1.65
     builder
    1.63
    creating
    1.58
     создавать
    1.55
     drag
    1.54
    create
    1.52
     creazione
    1.50
    Activations Density 0.058%

    No Known Activations