© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68119
    Prev
    Next
    INDEX
    Explanations

    #coding=utf-8

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

    The neuron selectively activates on numeric tokens—digits or numbers (e.g. “8,” “280,” “124.5,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     this
    -1.23
     their
    -1.14
     for
    -1.07
     many
    -1.05
     that
    -0.99
     often
    -0.99
     these
    -0.96
    andola
    -0.93
     Many
    -0.90
    ಘ
    -0.90
    POSITIVE LOGITS
    </h3>
    1.06
    と同じ
    1.02
    EVERY
    0.98
     chaves
    0.94
     rozs
    0.93
     itinéraires
    0.92
    AGAIN
    0.92
     réseaux
    0.92
    Kudos
    0.92
     contenir
    0.91
    Activations Density 0.001%

    No Known Activations