© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62934
    Prev
    Next
    INDEX
    Explanations

    E-Filing license code

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

    The neuron fires strongly on long runs of leading whitespace (indentation) in code or markup.

    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
     limited
    -1.52
    Limited
    -1.21
     Limited
    -1.11
    有限
    -1.08
    limited
    -1.02
     limitado
    -1.00
    LIMITED
    -0.89
     especially
    -0.88
     ограни
    -0.88
     options
    -0.87
    POSITIVE LOGITS
        
    1.13
            
    1.09
          
    0.85
    šė
    0.78
    mostly
    0.77
    рений
    0.76
    дә
    0.74
    稲田
    0.74
    pia
    0.73
     Wreath
    0.71
    Activations Density 0.099%

    No Known Activations