© 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. 12503
    Prev
    Next
    INDEX
    Explanations

    generation of groups

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

    The neuron strongly activates on the word “generation” (and its close variants like “generations”).

    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
    慙
    -1.94
    ꜆
    -1.88
    ῎
    -1.83
    ંગ
    -1.80
    ısından
    -1.78
    ㆆ
    -1.75
    涠
    -1.73
    뮐
    -1.73
    erweise
    -1.71
    cuerdo
    -1.71
    POSITIVE LOGITS
     –
    2.59
    ’
    2.50
     of
    2.44
     —
    2.30
    (
    2.19
     Generation
    2.17
     ‘’
    2.17
     generations
    2.11
     generation
    2.09
     «
    2.08
    Activations Density 0.017%

    No Known Activations