© 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. 107632
    Prev
    Next
    INDEX
    Explanations

    introduction to sections

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

    The neuron specializes in detecting numeric tokens (i.e. 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
    ös
    -0.78
    netics
    -0.76
    posicion
    -0.75
    ici
    -0.73
    cr
    -0.72
     accommodations
    -0.72
    ющие
    -0.71
    ativity
    -0.70
    тем
    -0.70
    amon
    -0.69
    POSITIVE LOGITS
    議員
    0.81
    FACE
    0.79
     fapt
    0.75
    yakarta
    0.74
     promising
    0.74
    toolStrip
    0.73
    ỹ
    0.73
     mặt
    0.73
     Upp
    0.71
     consistent
    0.71
    Activations Density 0.061%

    No Known Activations