© 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. 34-GEMMASCOPE-RES-131K
    7. 89938
    Prev
    Next
    INDEX
    Explanations

    executive director

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

    This neuron fires on tokens that are numerical or symbol-like (e.g. numbers, percentages, footnote marks).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     davantage
    -0.83
     하는
    -0.75
     температура
    -0.74
     доступ
    -0.74
     máis
    -0.72
     Uno
    -0.71
    minar
    -0.71
    performs
    -0.70
    ليل
    -0.70
     uno
    -0.70
    POSITIVE LOGITS
    örk
    0.77
    slim
    0.75
    ริ
    0.72
     Fractions
    0.72
    Sage
    0.69
    진
    0.69
     tert
    0.68
     copied
    0.68
     extraordinario
    0.68
    Waterloo
    0.68
    Activations Density 0.002%

    No Known Activations