© 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. 101236
    Prev
    Next
    INDEX
    Explanations

    conditional outcomes

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

    The main thing this neuron does is detect occurrences of the modal verb “should.”

    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
     is
    -1.68
    dropIfExists
    -1.63
     territo
    -1.55
    cillos
    -1.53
    ující
    -1.52
    viembre
    -1.48
    chaft
    -1.46
     traged
    -1.45
    ότητα
    -1.45
     Reſ
    -1.42
    POSITIVE LOGITS
    6
    2.05
    (
    2.02
    9
    1.91
    1
    1.80
     mojej
    1.80
    4
    1.78
    5
    1.69
     spokoj
    1.67
    3
    1.66
     any
    1.64
    Activations Density 0.011%

    No Known Activations