© 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. 10423
    Prev
    Next
    INDEX
    Explanations

    percentage value

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

    The neuron detects mentions of percentages (the word “percent” or percent‐value tokens).

    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
    现在的
    -2.06
    三个
    -1.94
    adomo
    -1.80
     .”
    -1.76
    AÇÃO
    -1.74
    AdvEx
    -1.70
    这些
    -1.70
    GORITH
    -1.69
     Это
    -1.67
    忖
    -1.67
    POSITIVE LOGITS
     of
    2.72
    '
    2.69
    -
    2.02
     the
    1.96
     "
    1.89
    ’
    1.73
     ("
    1.66
     使っ
    1.66
    ("
    1.64
    ,"
    1.64
    Activations Density 0.009%

    No Known Activations