© 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. 80586
    Prev
    Next
    INDEX
    Explanations

    do we

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

    This neuron detects question-related tokens, especially the interrogative word “what” and the following question mark.

    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
     this
    -1.80
     if
    -1.63
     what
    -1.52
     would
    -1.45
     could
    -1.31
     usually
    -1.28
     you
    -1.27
     and
    -1.24
     because
    -1.23
     acest
    -1.23
    POSITIVE LOGITS
    poids
    1.71
    Instead
    1.69
     produite
    1.62
     molte
    1.59
    Specifically
    1.55
    ᪥
    1.55
    approximately
    1.50
     eccell
    1.48
    圪
    1.45
     renfer
    1.44
    Activations Density 0.018%

    No Known Activations