© 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. 70070
    Prev
    Next
    INDEX
    Explanations

    code attributes and assignments

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

    This neuron activates on numeric literals (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_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
     głowy
    -1.08
     Artículos
    -0.88
     góry
    -0.88
    CGRect
    -0.87
     HIGHLIGHTS
    -0.84
     Consejos
    -0.81
     Materiales
    -0.81
    łożyć
    -0.81
     urządzenia
    -0.80
     drugiej
    -0.79
    POSITIVE LOGITS
     corrig
    1.03
     fix
    1.02
    میم
    1.01
     convert
    1.00
    fix
    1.00
    normalize
    0.99
     Cleanup
    0.96
     Obwohl
    0.93
     seemingly
    0.93
     normalize
    0.93
    Activations Density 0.021%

    No Known Activations