© 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. 34-GEMMASCOPE-RES-131K
    7. 116138
    Prev
    Next
    INDEX
    Explanations

    PC gaming

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

    The neuron fires on numeric tokens—counts, measurements, dates, IDs, and other numbers embedded 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_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
     very
    -0.88
     so
    -0.84
     νο
    -0.83
     NO
    -0.81
     kanyang
    -0.81
     However
    -0.80
     many
    -0.77
     suitable
    -0.77
     full
    -0.76
     cannot
    -0.76
    POSITIVE LOGITS
     počíta
    0.93
     ส่ง
    0.85
    PCs
    0.84
     startling
    0.84
     ktoré
    0.84
    gifs
    0.84
     elegantly
    0.83
    SPONSORED
    0.83
     enterprising
    0.83
    Nvidia
    0.80
    Activations Density 0.009%

    No Known Activations