© 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. 22-GEMMASCOPE-RES-131K
    7. 130984
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens (digits or numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    のよ
    -0.94
     metoda
    -0.91
     dilan
    -0.90
     rezultat
    -0.88
    essence
    -0.87
    🔓
    -0.87
    nữ
    -0.86
     spus
    -0.85
    ATTACHMENT
    -0.85
     requiere
    -0.84
    POSITIVE LOGITS
     по
    0.80
    ėk
    0.77
    我们
    0.75
    guitarra
    0.75
    ᱾
    0.75
    پر
    0.73
    OPSIS
    0.73
    maksud
    0.72
    専門
    0.71
     Weitere
    0.71
    Activations Density 0.007%

    No Known Activations