© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65013
    Prev
    Next
    INDEX
    Explanations

    a fraction of

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

    The neuron flags mentions of proportional quantities expressed as fractions (e.g. “a fraction of the cost”).

    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
     ήταν
    -1.67
    wendi
    -1.66
    icestershire
    -1.57
    тился
    -1.54
    sbury
    -1.49
    鈮
    -1.48
     esclusivamente
    -1.48
    bater
    -1.46
     összefoglal
    -1.46
     envíos
    -1.45
    POSITIVE LOGITS
    t
    2.27
     what
    1.80
    ons
    1.77
    u
    1.70
    }
    1.63
     the
    1.63
    x
    1.56
    mathrm
    1.55
    )
    1.53
     heutige
    1.51
    Activations Density 0.021%

    No Known Activations