© 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. 10-GEMMASCOPE-RES-131K
    7. 40886
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

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

    The neuron specializes in spotting digits that form the fractional part of decimal numbers (e.g. the “.9” in “5.9,” “.4” in “9.4,” or “.98” in “12.98”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵↵
    -1.71
    なんですが
    -1.62
    栒
    -1.57
    ܇
    -1.52
    ですかね
    -1.52
    Лечение
    -1.49
     видит
    -1.49
    
    -1.49
     “(
    -1.48
    鲮
    -1.47
    POSITIVE LOGITS
    "
    2.36
    这种
    2.11
     эти
    2.08
    ("
    2.06
     этого
    2.06
     этих
    1.98
    這種
    1.84
    ]
    1.83
     этот
    1.79
    神器
    1.74
    Activations Density 0.052%

    No Known Activations