© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 99487
    Prev
    Next
    INDEX
    Explanations

    code comments containing definitions

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

    This neuron fires on numeric literal tokens (numbers) 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
    																															
    -0.93
     while
    -0.92
     again
    -0.89
     later
    -0.88
    [])
    
    -0.87
    ाहरण
    -0.84
     noiembrie
    -0.81
    ()!=
    -0.81
    ̀ng
    -0.81
     wiederum
    -0.79
    POSITIVE LOGITS
    const
    2.02
     const
    1.59
    protected
    1.43
     protected
    1.37
    use
    1.25
     use
    1.21
    var
    1.13
    Const
    1.02
    CONST
    1.00
     gebruik
    1.00
    Activations Density 0.017%

    No Known Activations