© 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. 130513
    Prev
    Next
    INDEX
    Explanations

    This neuron detects definition‐request questions, especially occurrences of “what … mean” in queries.

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

    meaning of syntax and words

    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
    ertale
    -0.98
     would
    -0.94
     can
    -0.92
     getItemId
    -0.90
    GRAFÍA
    -0.88
     direct
    -0.85
    crollView
    -0.84
     definizione
    -0.84
    应
    -0.82
     вышел
    -0.82
    POSITIVE LOGITS
     strange
    1.10
     clínicas
    1.09
     waarom
    1.08
     стран
    1.07
     waarvan
    1.07
     plötzlich
    1.03
     mysterious
    1.02
    特别
    1.01
    看起來
    1.00
    vieron
    0.99
    Activations Density 0.092%

    No Known Activations