© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 117356
    Prev
    Next
    INDEX
    Explanations

    Florence Hartmann

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

    The neuron fires on error‐handling code patterns, especially the “if err != nil” style checks.

    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
    ())
    
    -0.93
    )
    -0.77
    འི་
    -0.74
    を
    -0.73
    ),
    -0.69
    結局
    -0.68
    後悔
    -0.68
    癒
    -0.68
    ).
    -0.68
    )
    
    -0.67
    POSITIVE LOGITS
     nil
    1.94
    nil
    1.41
     nullptr
    1.17
     etc
    1.01
     nothing
    0.91
     NULL
    0.91
    HasForeignKey
    0.91
    context
    0.88
    ViewImports
    0.85
     nowhere
    0.84
    Activations Density 0.005%

    No Known Activations