© 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. 10362
    Prev
    Next
    INDEX
    Explanations

    pay attention to

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

    The neuron activates on the phrase “pay attention 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
    ;
    -2.23
    )
    -2.14
     a
    -1.94
    :
    -1.94
    >
    -1.85
     Some
    -1.80
    Other
    -1.77
    (
    -1.73
    "
    -1.73
    ?
    -1.69
    POSITIVE LOGITS
     czter
    1.97
    栳
    1.88
     trzech
    1.88
    甃
    1.77
     how
    1.73
     naše
    1.68
     belangrijke
    1.66
     vaše
    1.65
     troisième
    1.64
     godziny
    1.64
    Activations Density 0.013%

    No Known Activations