© 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. 23897
    Prev
    Next
    INDEX
    Explanations

    check to see if

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

    This neuron detects the phrase pattern “check (or look, checks) to see if.”

    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
     on
    -2.25
     by
    -1.76
     helped
    -1.63
     (
    -1.55
     staunch
    -1.54
     may
    -1.52
     through
    -1.52
     enormous
    -1.48
    <bos>
    -1.46
     even
    -1.44
    POSITIVE LOGITS
     zoude
    1.90
     informé
    1.81
    蔟
    1.80
    婓
    1.77
    ientras
    1.72
    幛
    1.71
     dezelve
    1.68
    轵
    1.66
     menyen
    1.66
     adatta
    1.64
    Activations Density 0.010%

    No Known Activations