© 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. 10-GEMMASCOPE-RES-131K
    7. 1840
    Prev
    Next
    INDEX
    Explanations

    data structures

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

    The neuron fires on mentions of “data structures” or closely related terminology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     longtime
    -1.52
    ୫
    -1.49
    MessageInfo
    -1.46
     posiblemente
    -1.45
    螣
    -1.44
     the
    -1.41
     afbeelding
    -1.41
     agarre
    -1.39
     riego
    -1.38
     acabamento
    -1.38
    POSITIVE LOGITS
     också
    1.41
    </h4>
    1.41
    also
    1.37
     revive
    1.27
     también
    1.27
     hizo
    1.25
     revise
    1.25
     дают
    1.23
     soothe
    1.23
     гаран
    1.23
    Activations Density 0.065%

    No Known Activations