© 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. 22-GEMMASCOPE-RES-131K
    7. 14466
    Prev
    Next
    INDEX
    Explanations

    parentheses and code keywords

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

    The neuron activates on numeric literals (number tokens) 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_22/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
     régal
    -0.99
    sellors
    -0.99
    却被
    -0.96
     vaše
    -0.96
     Алексей
    -0.96
     prostu
    -0.95
     чолові
    -0.95
     magnifiques
    -0.94
    Firstly
    -0.94
    椤
    -0.92
    POSITIVE LOGITS
    éfonos
    1.14
    
    1.06
    '~
    1.05
     cantora
    0.99
    ]-->
    0.96
     atriz
    0.94
    ']='
    0.93
     true
    0.93
    *]
    0.92
    –
    0.92
    Activations Density 0.002%

    No Known Activations