© 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. 34-GEMMASCOPE-RES-131K
    7. 8043
    Prev
    Next
    INDEX
    Explanations

    foreign origin or placeholder

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

    The neuron is detecting numeric literals (i.e. sequences of digits).

    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
    9
    -1.20
     nine
    -1.02
     NINE
    -0.90
     Nine
    -0.85
    ９
    -0.83
     nineteen
    -0.83
    Nine
    -0.83
    ৯
    -0.83
     PyObject
    -0.78
     Nineteen
    -0.77
    POSITIVE LOGITS
    rstrip
    0.72
    ById
    0.70
    ひと
    0.69
     laced
    0.68
     Tại
    0.67
     Lateral
    0.67
     toàn
    0.66
     foretold
    0.65
     hunch
    0.65
    Ancient
    0.65
    Activations Density 1.559%

    No Known Activations