© 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. 59959
    Prev
    Next
    INDEX
    Explanations

    document entries and items

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

    The neuron activates on long sequences of digits—i.e. numeric identifiers such as accession numbers, catalogue codes, years, or other multi-digit numbers.

    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
    limite
    -0.74
    livejournal
    -0.71
     Pok
    -0.69
    subsubsection
    -0.69
     Stedman
    -0.68
     isIn
    -0.68
    脚注の使い方
    -0.67
     STATIC
    -0.67
    ServletConfig
    -0.67
     Dea
    -0.66
    POSITIVE LOGITS
     folio
    1.09
     foli
    1.04
     fol
    1.03
     recto
    0.87
     partea
    0.82
    folio
    0.81
    lr
    0.80
     zapis
    0.79
    fol
    0.79
    ItemModel
    0.78
    Activations Density 0.031%

    No Known Activations