© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32321
    Prev
    Next
    INDEX
    Explanations

    item descriptions

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

    This neuron detects key named-entity tokens in product or listing contexts—such as product names, category headings, or model identifiers.

    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
     publique
    -0.88
     atmosf
    -0.85
     ftre
    -0.81
     trenger
    -0.80
     laft
    -0.79
    而非
    -0.78
    >
    -0.77
    /***/
    -0.76
    backward
    -0.76
     robe
    -0.75
    POSITIVE LOGITS
    tivazione
    0.85
     размере
    0.82
    ceries
    0.81
     mencionados
    0.80
    gunta
    0.79
     diseñados
    0.78
    ntos
    0.77
     abiertos
    0.77
    bạn
    0.77
    oming
    0.77
    Activations Density 0.004%

    No Known Activations