© 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. 102408
    Prev
    Next
    INDEX
    Explanations

    what happens after an action

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

    The main thing this neuron does is spot numeric tokens (digits and 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_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
     currently
    -1.80
     while
    -1.64
     tetapi
    -1.63
     to
    -1.63
     atualmente
    -1.62
    "},
    -1.59
     actualmente
    -1.59
    konos
    -1.52
     is
    -1.52
     but
    -1.52
    POSITIVE LOGITS
     roues
    1.77
     âme
    1.76
    文學
    1.75
    為主
    1.75
    $
    1.73
     geladeira
    1.71
     plastiques
    1.68
     oreille
    1.68
     chaussure
    1.67
     pleins
    1.67
    Activations Density 0.042%

    No Known Activations