© 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. 84730
    Prev
    Next
    INDEX
    Explanations

    sorting, filtering, and searching data

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

    This neuron fires on code tokens that name or configure sorting/filtering operations (e.g. “sort,” “order,” “filter,” “orderby,” “limit”).

    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
    __":
    -0.97
    silien
    -0.88
    ILLO
    -0.86
    ngiliz
    -0.82
    лару
    -0.82
    OLEAN
    -0.80
    WarningLevel
    -0.80
    autom
    -0.77
     Minion
    -0.77
     organização
    -0.76
    POSITIVE LOGITS
     by
    2.05
     direction
    1.19
     on
    1.04
    by
    1.01
     clause
    0.94
     criteria
    0.93
    By
    0.92
    Direction
    0.84
     mechanism
    0.84
    Field
    0.83
    Activations Density 0.017%

    No Known Activations