© 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. 34-GEMMASCOPE-RES-131K
    7. 108976
    Prev
    Next
    INDEX
    Explanations

    names and code constructs

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

    The neuron fires on programming‐language syntax tokens—especially generic type declarations and related symbols (e.g. angle brackets, type names, include directives) 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
     arguably
    -0.84
     oddly
    -0.81
     utterly
    -0.81
     Vengeance
    -0.79
     every
    -0.78
     all
    -0.76
     enhanced
    -0.75
     weirdly
    -0.73
     gave
    -0.72
     enhancing
    -0.72
    POSITIVE LOGITS
     Toledo
    1.09
    Toledo
    1.05
    Microsoft
    1.04
     Chicago
    1.03
     Illinois
    1.02
    Illinois
    0.99
     Windows
    0.98
    ifflin
    0.91
     ACTIV
    0.91
    INTERFACE
    0.91
    Activations Density 0.002%

    No Known Activations