© 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. 13062
    Prev
    Next
    INDEX
    Explanations

    programming constructs and keywords

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

    The neuron activates on numeric literals (numbers and numeric constants) in the 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
    
    -0.93
    Ꮴ
    -0.93
    ionario
    -0.91
    ウター
    -0.91
    SetTitle
    -0.90
     Winaray
    -0.89
     Beaucoup
    -0.88
    uin
    -0.87
     OAuth
    -0.86
     brilho
    -0.86
    POSITIVE LOGITS
     perlindungan
    1.00
     but
    1.00
     porcentual
    0.99
     in
    0.97
     or
    0.97
     on
    0.93
     while
    0.93
     through
    0.93
     without
    0.92
     during
    0.90
    Activations Density 0.008%

    No Known Activations