© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92201
    Prev
    Next
    INDEX
    Explanations

    data field or column

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

    The neuron is triggered by code-style identifiers and JSON/parameter field names (e.g. “size”, “field”, “date_histogram”, “query”, “aggregation”).

    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
    Joh
    -0.85
    Παρα
    -0.80
     الرائ
    -0.75
    álbum
    -0.73
     roughly
    -0.73
    encils
    -0.72
    esModule
    -0.71
    牡丹
    -0.71
    copio
    -0.70
    ramentas
    -0.70
    POSITIVE LOGITS
     field
    2.89
     column
    2.55
     fields
    2.41
    字段
    2.25
    column
    2.08
    Field
    2.06
    field
    1.97
     columns
    1.88
     attribute
    1.88
    fieldName
    1.81
    Activations Density 0.180%

    No Known Activations