© 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. 39932
    Prev
    Next
    INDEX
    Explanations

    quantities of more

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

    The neuron activates on the word “more” when it’s used to indicate additional items or quantities.

    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
    ↵↵
    -2.08
    1
    -2.05
    [
    -1.90
    0
    -1.88
     following
    -1.75
    .
    -1.73
    -
    -1.73
     it
    -1.73
    </h4>
    -1.70
    ,
    -1.70
    POSITIVE LOGITS
    馐
    2.05
    眛
    2.02
    怍
    2.02
     unangemessene
    2.00
    緲
    1.99
    亊
    1.96
    addPreferred
    1.95
    鹇
    1.95
     feltro
    1.91
    餿
    1.91
    Activations Density 0.007%

    No Known Activations