© 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. 43403
    Prev
    Next
    INDEX
    Explanations

    arguments or list items

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

    The neuron primarily detects numeric literal tokens (e.g. integers and floating‐point numbers) 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_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
    _
    -2.63
    *
    -2.30
    鶿
    -2.28
    all
    -2.13
    我们的
    -2.05
     vores
    -1.98
    //
    -1.98
    (!)
    -1.96
    ooo
    -1.95
    Ба
    -1.94
    POSITIVE LOGITS
     are
    2.39
     protože
    2.23
    荩
    2.09
    🫅
    2.00
     they
    1.98
    はある
    1.98
     ciutat
    1.94
    舠
    1.94
    zmm
    1.91
    赑
    1.90
    Activations Density 0.028%

    No Known Activations