© 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. 22-GEMMASCOPE-RES-131K
    7. 65938
    Prev
    Next
    INDEX
    Explanations

    quantities and servings

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

    The neuron activates on numeric tokens (quantities, measurements, counts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    lių
    -1.00
    NewReader
    -0.96
    detto
    -0.96
    瞥
    -0.95
     getAll
    -0.94
     المسؤول
    -0.94
     hatt
    -0.93
    搀
    -0.93
     Haziran
    -0.93
    enaire
    -0.90
    POSITIVE LOGITS
     assuming
    1.01
    erapeu
    0.95
     dwóch
    0.94
     izman
    0.93
    걍
    0.93
     скром
    0.93
     międzynarod
    0.93
    yaszt
    0.92
     with
    0.92
     approximately
    0.92
    Activations Density 0.006%

    No Known Activations