© 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. 128972
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is detect numeric tokens (numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    court records, label select

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     this
    -1.37
     will
    -1.25
    kaç
    -1.20
     two
    -1.18
     would
    -1.16
     during
    -1.15
     made
    -1.14
     had
    -1.14
     a
    -1.13
     almohada
    -1.11
    POSITIVE LOGITS
     выбрать
    1.59
    などは
    1.27
     escolher
    1.27
     подобрать
    1.26
    erobic
    1.25
    Organisateur
    1.22
    eches
    1.20
    glected
    1.20
    苙
    1.16
     ofreció
    1.14
    Activations Density 0.060%

    No Known Activations