© 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. 58895
    Prev
    Next
    INDEX
    Explanations

    court dates and times

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

    The neuron activates on numeric tokens, especially multi‐digit numbers in dates, filings, and case 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
     from
    -0.91
     subtly
    -0.84
     regions
    -0.80
     Component
    -0.77
     Prozess
    -0.76
    呼ぶ
    -0.75
     first
    -0.73
     сухой
    -0.72
    keyDown
    -0.72
     in
    -0.72
    POSITIVE LOGITS
     اض
    0.88
    ٹ
    0.87
    Indiana
    0.87
    verlag
    0.86
    ței
    0.82
     üzerine
    0.82
     almendras
    0.82
     með
    0.82
    vesh
    0.81
    gest
    0.80
    Activations Density 0.006%

    No Known Activations