© 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. 34567
    Prev
    Next
    INDEX
    Explanations

    patent numbers

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

    The neuron specializes in spotting numeric tokens (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
     there
    -1.03
    七十
    -0.99
     oport
    -0.94
    旰
    -0.94
    高山
    -0.93
     resembling
    -0.93
    泐
    -0.93
     aches
    -0.90
    八十
    -0.90
    醍
    -0.87
    POSITIVE LOGITS
    without
    0.90
    と思い
    0.84
    hlte
    0.84
     ";"
    0.82
    misch
    0.81
    RESUMEN
    0.80
    real
    0.78
    olds
    0.78
     lakini
    0.76
     ilustracji
    0.76
    Activations Density 0.024%

    No Known Activations