© 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. 127820
    Prev
    Next
    INDEX
    Explanations

    describing physical size

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

    The neuron activates on numeric tokens representing size or dimensional measurements (especially large values).

    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
     
    -1.58
    ┍
    -1.44
    léans
    -1.38
     Hauteur
    -1.30
    cruise
    -1.28
    をチェック
    -1.28
     fameux
    -1.20
     Sélection
    -1.20
    thmus
    -1.19
    に合わせて
    -1.17
    POSITIVE LOGITS
     can
    1.63
     usually
    1.49
    ACIONAL
    1.38
     обычно
    1.34
     ordinarily
    1.34
     когда
    1.30
     our
    1.28
    èses
    1.28
     should
    1.27
    бычно
    1.27
    Activations Density 0.062%

    No Known Activations