© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75297
    Prev
    Next
    INDEX
    Explanations

    JSDoc comments and code syntax

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

    The neuron activates on numeric literals 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
     where
    -0.98
     Sejarah
    -0.93
     significato
    -0.88
     minuman
    -0.88
     Pilihan
    -0.85
    atleta
    -0.85
    because
    -0.85
     Banyak
    -0.85
     reflected
    -0.84
     schlaf
    -0.84
    POSITIVE LOGITS
    ᠮ
    0.99
     озе
    0.95
    vergne
    0.93
    lishes
    0.91
     particules
    0.90
     équipe
    0.89
     auteurs
    0.88
     Kohli
    0.88
    
    0.87
     esas
    0.86
    Activations Density 0.002%

    No Known Activations