© 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. 55558
    Prev
    Next
    INDEX
    Explanations

    resource urls, scripts, links

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

    The neuron strongly activates on numeric tokens and technical metadata—things like version numbers, URLs/file paths, DOCTYPE or license markers, and other numeric or code‐header identifiers.

    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
     FONT
    -0.79
     Visible
    -0.76
     AGRE
    -0.76
     перед
    -0.75
    agre
    -0.74
    Ý
    -0.74
    readOnly
    -0.72
    foot
    -0.72
    CEN
    -0.71
    APY
    -0.71
    POSITIVE LOGITS
     process
    0.89
    lindungi
    0.81
    Process
    0.79
     monasterio
    0.79
     künftig
    0.71
     cejas
    0.70
    ENTINA
    0.70
     أثناء
    0.70
    exion
    0.69
    process
    0.69
    Activations Density 0.023%

    No Known Activations