© 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. 34-GEMMASCOPE-RES-131K
    7. 99278
    Prev
    Next
    INDEX
    Explanations

    hexadecimal values and delimiters

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

    The neuron fires on numeric literal tokens (decimal or hexadecimal constants) in source 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
    などが
    -0.90
    
    -0.85
    などなど
    -0.84
    オープ
    -0.80
     ίδ
    -0.76
    结语
    -0.76
    cipais
    -0.76
    زة
    -0.76
     CERTAIN
    -0.76
     wonderful
    -0.75
    POSITIVE LOGITS
    
    0.77
     upland
    0.73
    getNome
    0.72
    )−
    0.71
     Oliveira
    0.71
    避
    0.71
    abelle
    0.71
     понравился
    0.70
    耻
    0.70
     géographique
    0.69
    Activations Density 0.015%

    No Known Activations