© 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. 34-GEMMASCOPE-RES-131K
    7. 84132
    Prev
    Next
    INDEX
    Explanations

    code keywords and functions

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

    The neuron strongly activates on numeric literals (digits or numbers) in code snippets.

    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
     their
    -1.04
    ifikationen
    -0.93
     facilitating
    -0.88
     sending
    -0.83
     drastically
    -0.83
     individuals
    -0.82
     intrinsically
    -0.82
    蘿
    -0.80
     ironically
    -0.80
     considerably
    -0.80
    POSITIVE LOGITS
    ɵɵ
    0.94
    området
    0.90
    ']=
    0.88
    Ŕ
    0.88
     може
    0.88
    +',
    0.88
    lín
    0.87
     pecados
    0.86
     โดย
    0.86
    лайд
    0.85
    Activations Density 0.005%

    No Known Activations