© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73481
    Prev
    Next
    INDEX
    Explanations

    the word "use"

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

    The neuron strongly activates on the uppercase token “USE,” marking occurrences of that specific keyword.

    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
    s
    -4.16
     then
    -3.70
    唎
    -3.20
    ſſen
    -3.20
    沩
    -3.17
    嚶
    -3.16
    泅
    -3.08
    涠
    -3.05
    breviations
    -2.98
    甍
    -2.97
    POSITIVE LOGITS
    There
    4.63
     
    4.31
    Because
    4.25
    Since
    4.25
    With
    4.22
    During
    4.22
    Initially
    4.19
    5
    4.13
    When
    4.06
    Within
    4.06
    Activations Density 0.016%

    No Known Activations