© 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. 116231
    Prev
    Next
    INDEX
    Explanations

    eager anticipation and excitement

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

    The neuron strongly activates on numeric tokens—especially multi‐digit numbers such as years, counts, or statistics—and thus detects numerical information 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
    шений
    -0.96
     джере
    -0.85
    demon
    -0.83
    íticas
    -0.77
     Formosa
    -0.77
    움
    -0.73
     Millet
    -0.70
    改めて
    -0.70
    észet
    -0.70
    ueel
    -0.69
    POSITIVE LOGITS
     anticipation
    4.84
     excitement
    3.64
     excited
    3.39
     anticipating
    3.09
     anticip
    3.02
     anticipate
    2.94
    期待
    2.91
     expectation
    2.89
     eagerly
    2.88
     expectations
    2.73
    Activations Density 0.109%

    No Known Activations