© 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. 99660
    Prev
    Next
    INDEX
    Explanations

    programming code examples

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

    The neuron detects numeric literal tokens (i.e. numbers/constants) in code.

    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
    [][]
    -0.94
    usammen
    -0.91
    ]['
    -0.88
    Итак
    -0.87
    \'{
    -0.84
    [][
    -0.84
     también
    -0.81
     []
    -0.77
     tienes
    -0.77
     as
    -0.76
    POSITIVE LOGITS
    [,]
    1.46
     Особенно
    0.88
    [,
    0.87
     Потому
    0.79
    especially
    0.78
    particularly
    0.77
    (,
    0.74
     Umum
    0.74
     isolado
    0.74
     ची
    0.73
    Activations Density 0.012%

    No Known Activations