© 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. 31565
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

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

    The neuron fires on code tokens that introduce function or module calls—i.e. the opening of an argument list (parentheses or brackets) 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_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
    eslint
    -0.90
    feren
    -0.87
    primaryStage
    -0.86
    Their
    -0.86
     conftest
    -0.85
    バーグ
    -0.85
    handlung
    -0.85
     XCTest
    -0.84
    AppComponent
    -0.84
    īgas
    -0.82
    POSITIVE LOGITS
     essentials
    1.02
          
    0.86
         
    0.84
    EMBLY
    0.84
     necessaria
    0.78
     rius
    0.78
            
    0.77
                  
    0.77
             
    0.76
     another
    0.76
    Activations Density 0.002%

    No Known Activations