© 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. 22-GEMMASCOPE-RES-131K
    7. 129959
    Prev
    Next
    INDEX
    Explanations

    This neuron spotlights identifiers used as field or key names (e.g. column names or configuration parameter names) in code and schema definitions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    variable names and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Y
    -0.96
     jemanden
    -0.91
    Y
    -0.89
    W
    -0.86
     SLR
    -0.85
     Please
    -0.84
    pædia
    -0.84
    sql
    -0.83
    ES
    -0.82
     as
    -0.82
    POSITIVE LOGITS
     verhe
    1.03
     verhind
    1.00
     kleid
    0.96
     pady
    0.96
     dichter
    0.96
    recently
    0.95
     encaje
    0.94
     ofic
    0.93
     klok
    0.93
     geheim
    0.93
    Activations Density 0.041%

    No Known Activations