© 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. 60649
    Prev
    Next
    INDEX
    Explanations

    properties and characteristics

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

    The neuron flags numeric measurement tokens (e.g. numbers, decimals, coefficients, and units) in scientific text.

    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
     Eſ
    -1.66
    ſa
    -1.65
     you
    -1.64
    ſo
    -1.40
     hôtel
    -1.38
     DataGridView
    -1.34
    commodation
    -1.32
    iſ
    -1.31
    pherals
    -1.30
    pointment
    -1.27
    POSITIVE LOGITS
     by
    1.73
    theoremstyle
    1.37
     zawiera
    1.37
    Various
    1.30
     both
    1.28
    生平
    1.27
    也會
    1.27
    Each
    1.26
     diferentes
    1.25
     Jerusalén
    1.24
    Activations Density 0.277%

    No Known Activations