© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45522
    Prev
    Next
    INDEX
    Explanations

    in terms of

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

    The neuron detects numeric measurement phrases of the form “[number] terms of [number],” i.e. paired numerical values used to quantify or compare something.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    選ば
    -1.77
     Why
    -1.54
     dipilih
    -1.52
     дуже
    -1.49
    Several
    -1.48
     слишком
    -1.45
    What
    -1.43
     terlalu
    -1.42
     Various
    -1.40
     Extremely
    -1.39
    POSITIVE LOGITS
    en
    2.03
    </strong>
    1.71
    lu
    1.69
    f
    1.65
    秾
    1.59
    can
    1.59
     to
    1.58
     hanno
    1.58
    li
    1.47
     ï
    1.47
    Activations Density 0.082%

    No Known Activations