© 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. 10-GEMMASCOPE-RES-131K
    7. 43770
    Prev
    Next
    INDEX
    Explanations

    code prefixes and suffixes

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

    This neuron activates on D3.js data‐join lifecycle calls and related selection method tokens (e.g. enter, exit, append, remove) in force-directed graph code.

    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
     –
    -2.05
     &
    -2.02
    ak
    -1.97
    ations
    -1.90
    writeHead
    -1.87
    ;
    -1.82
     (
    -1.81
    .
    -1.81
    n
    -1.78
    :
    -1.78
    POSITIVE LOGITS
     animado
    2.08
    bakter
    2.06
    嵓
    2.02
    僦
    2.02
     pesada
    2.00
     rígido
    1.99
     robusto
    1.95
     intertwined
    1.95
     resina
    1.91
    餿
    1.91
    Activations Density 0.009%

    No Known Activations