© 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. 107236
    Prev
    Next
    INDEX
    Explanations

    programming language syntax

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

    The neuron is selectively activating on code‐style identifiers—especially PascalCase/CamelCase names and keywords in programming language snippets.

    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
     vantagens
    -0.92
     procedimentos
    -0.82
     až
    -0.81
     fatores
    -0.80
    roach
    -0.80
     besos
    -0.80
    Pinterest
    -0.77
    veal
    -0.77
     anúncios
    -0.77
     juguete
    -0.77
    POSITIVE LOGITS
     PropertyChanged
    1.00
    श्लेषण
    0.85
    Ria
    0.84
     POD
    0.84
    Nave
    0.82
     Ó
    0.79
     között
    0.77
    Topo
    0.77
     Nave
    0.77
     Topo
    0.77
    Activations Density 0.001%

    No Known Activations