© 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. 48379
    Prev
    Next
    INDEX
    Explanations

    view.composer or config. new

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

    The neuron is strongly triggered by numeric tokens—any sequence of digits or numbers in the text.

    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
     reclamar
    -0.75
    Чи
    -0.74
     ද
    -0.73
    Miy
    -0.73
    Aihe
    -0.73
    Router
    -0.73
    Jahre
    -0.72
     የ
    -0.71
    Linn
    -0.71
    wendung
    -0.71
    POSITIVE LOGITS
     presenter
    0.81
     scope
    0.81
     presenters
    0.80
    elo
    0.79
     Scope
    0.79
     Presenter
    0.77
     қара
    0.75
     query
    0.73
    textrm
    0.73
    scope
    0.71
    Activations Density 0.027%

    No Known Activations