© 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. 27784
    Prev
    Next
    INDEX
    Explanations

    file system operations

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

    The neuron consistently lights up on numeric tokens—i.e. literals or numbers appearing in code or text.

    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
    釁
    -1.04
     completamente
    -0.93
     crescente
    -0.85
    試試
    -0.84
     most
    -0.83
     totalmente
    -0.82
    leb
    -0.82
    的能力
    -0.81
    ='';
    -0.81
    splitting
    -0.81
    POSITIVE LOGITS
    fonts
    1.00
    ínsula
    0.97
     ())
    0.94
    İş
    0.93
     även
    0.91
    hawatir
    0.90
    
    0.90
    کتاب
    0.88
    èrent
    0.88
    lated
    0.87
    Activations Density 0.015%

    No Known Activations