© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129914
    Prev
    Next
    INDEX
    Explanations

    The neuron detects very high‐frequency/common tokens (common function words and other frequent tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the Oscars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     settimane
    -0.99
     puncak
    -0.93
    currentValue
    -0.91
    ubon
    -0.90
     weird
    -0.90
    without
    -0.88
    ANSION
    -0.88
     Without
    -0.87
     strange
    -0.86
     गर्न
    -0.86
    POSITIVE LOGITS
    inerario
    1.13
     constructeur
    0.97
    общение
    0.96
     lança
    0.95
    varies
    0.91
     vérit
    0.91
    mende
    0.90
    xiety
    0.89
     emocion
    0.88
    aturday
    0.87
    Activations Density 0.071%

    No Known Activations