© 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. 81555
    Prev
    Next
    INDEX
    Explanations

    webkit chrome rendering

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

    The neuron strongly activates on numeric tokens (e.g. years, version numbers, and other multi‐digit numbers).

    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
    ColumnHeaders
    -0.81
    hdl
    -0.76
     cyber
    -0.75
    Cyber
    -0.75
     immédi
    -0.74
     sponsor
    -0.74
    <>
    -0.73
    textbackslash
    -0.72
     cybersecurity
    -0.72
    徨
    -0.72
    POSITIVE LOGITS
    rendering
    1.07
     rendering
    1.04
     presto
    1.00
    presto
    0.89
     Presto
    0.82
     Garnet
    0.79
     border
    0.78
    dillo
    0.77
     Palm
    0.77
    pista
    0.75
    Activations Density 0.133%

    No Known Activations