© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111639
    Prev
    Next
    INDEX
    Explanations

    Division numbers

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

    The neuron detects numbered classification labels—tokens like “Class,” “Division,” or subsection identifiers followed by digits.

    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
     destrucción
    -1.61
    řízení
    -1.57
     Kartoffeln
    -1.41
    kových
    -1.38
     habían
    -1.34
    ADELPHIA
    -1.34
     kteří
    -1.34
     które
    -1.33
    entistas
    -1.33
     které
    -1.30
    POSITIVE LOGITS
     spion
    1.57
    The
    1.52
     robuste
    1.49
    ⚋
    1.48
     aktivi
    1.47
     comunica
    1.46
     parut
    1.45
     silvestre
    1.44
    </sub>
    1.43
     bénéficiaire
    1.43
    Activations Density 0.026%

    No Known Activations