© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 80772
    Prev
    Next
    INDEX
    Explanations

    sample, test, usernames, true values, router

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

    The neuron activates on numeric literals in the text (e.g. integers or decimals).

    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
     is
    -2.00
     which
    -1.74
    ↵
    -1.73
     was
    -1.66
     has
    -1.59
    ！”
    -1.59
    sen
    -1.56
     indicates
    -1.49
     be
    -1.48
    t
    -1.48
    POSITIVE LOGITS
    鱚
    1.86
     türkiye
    1.77
    侂
    1.64
    subequations
    1.63
     ТАК
    1.62
    抡
    1.58
    ⒎
    1.58
     概要
    1.55
    outSlope
    1.54
     bepaalde
    1.54
    Activations Density 0.019%

    No Known Activations