© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90319
    Prev
    Next
    INDEX
    Explanations

    class Meta structure

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

    This neuron fires on code defining classes, i.e. the “class” keyword 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
    ortage
    -0.83
     Vals
    -0.77
    bira
    -0.69
    FOL
    -0.68
    hésite
    -0.68
     liderança
    -0.67
     welcomes
    -0.67
     Langley
    -0.67
    ῆς
    -0.66
    Decrease
    -0.66
    POSITIVE LOGITS
     Meta
    1.11
    Meta
    0.94
     meta
    0.86
    meta
    0.78
     Iowa
    0.67
    tivity
    0.67
     Wilton
    0.66
    tivo
    0.66
    Steps
    0.65
     embar
    0.65
    Activations Density 0.085%

    No Known Activations