© 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. 22-GEMMASCOPE-RES-131K
    7. 28324
    Prev
    Next
    INDEX
    Explanations

    match/no match outcomes

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

    The neuron fires on standalone numeric literals (integer constants) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    encer
    -0.90
    chaic
    -0.83
    picious
    -0.83
    蜮
    -0.81
    anoma
    -0.76
    iaus
    -0.76
    ופן
    -0.75
    พร้อม
    -0.75
    Something
    -0.75
    litre
    -0.75
    POSITIVE LOGITS
     other
    0.96
    istung
    0.87
    REJECT
    0.84
     worthless
    0.80
     أخرى
    0.79
     andere
    0.77
     Nebraska
    0.77
    beginPath
    0.76
    ipto
    0.76
     другим
    0.74
    Activations Density 0.006%

    No Known Activations