© 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. 66354
    Prev
    Next
    INDEX
    Explanations

    we prove that

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

    The neuron detects numeric tokens (multi‐digit numbers) 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_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
    l
    -2.13
     We
    -2.03
    );
    -2.02
    ”、“
    -1.92
    で
    -1.91
    í
    -1.88
    ,”
    -1.86
    ،
    -1.85
    を
    -1.84
    dicionado
    -1.83
    POSITIVE LOGITS
     there
    2.59
     it
    2.14
    ducers
    2.03
    ⩴
    1.95
    said
    1.91
     henceforth
    1.88
     while
    1.83
     since
    1.80
     because
    1.79
    眛
    1.79
    Activations Density 0.202%

    No Known Activations