© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110901
    Prev
    Next
    INDEX
    Explanations

    functional programming syntax

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

    The neuron fires on code‐style tokens (programming keywords, uppercase identifiers, and punctuation) indicating it’s spotting code fragments.

    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
     Contro
    -0.84
    Contro
    -0.84
    whereas
    -0.84
     sedangkan
    -0.82
     whereas
    -0.79
     =",
    -0.79
     ontwikkel
    -0.75
    ²/
    -0.75
    tanaman
    -0.74
    queer
    -0.74
    POSITIVE LOGITS
    (_,
    1.35
     _)
    1.20
     _,
    1.20
    _->
    1.15
    ..)
    1.05
     (_)
    1.05
     (_,
    1.03
     (_
    1.02
    (_)
    0.99
    _)
    0.98
    Activations Density 0.005%

    No Known Activations