© 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. 70120
    Prev
    Next
    INDEX
    Explanations

    to followed by action verbs

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

    This neuron fires on occurrences of the word “to.”

    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
     of
    -3.23
    .
    -3.03
     \{
    -3.03
    巨大的
    -2.70
    {
    -2.59
    ("
    -2.56
    <bos>
    -2.42
    ⑊
    -2.34
    独特的
    -2.31
     "'
    -2.27
    POSITIVE LOGITS
    鈰
    2.94
     be
    2.81
     μην
    2.52
    釓
    2.50
    噥
    2.47
    琑
    2.42
     зді
    2.36
    焄
    2.31
     avoid
    2.30
     know
    2.25
    Activations Density 1.518%

    No Known Activations