© 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. 10-GEMMASCOPE-RES-131K
    7. 19869
    Prev
    Next
    INDEX
    Explanations

    ways to investigate

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

    The neuron is primarily detecting numeric tokens (e.g. version numbers, decimal values, plain integers) 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
     carefree
    -1.05
    shaped
    -1.02
     multifaceted
    -1.00
     catchy
    -0.98
    بت
    -0.97
     classy
    -0.97
     entrust
    -0.96
     Contrary
    -0.95
     ambiance
    -0.94
     Besides
    -0.94
    POSITIVE LOGITS
    вшийся
    1.14
     noting
    1.09
     exciter
    1.08
    $--
    1.02
    黼
    1.00
     oogen
    1.00
    🦃
    0.96
     gotten
    0.96
     WEBSITE
    0.96
    ꦗ
    0.96
    Activations Density 14.905%

    No Known Activations