© 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. 10-GEMMASCOPE-RES-131K
    7. 75167
    Prev
    Next
    INDEX
    Explanations

    programming class declarations

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

    The neuron detects occurrences of the keyword “class” (i.e. class declarations) in source‐code 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_10/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
    皤
    -1.75
     medlemmer
    -1.73
     lære
    -1.66
    ୩
    -1.66
    ꜄
    -1.54
    kemeja
    -1.52
     ventilador
    -1.52
     volando
    -1.50
    ㅿ
    -1.48
     gancho
    -1.47
    POSITIVE LOGITS
    :
    2.17
     —
    2.03
     that
    1.91
    os
    1.87
     are
    1.81
    ]
    1.77
    .”
    1.77
     the
    1.72
    ans
    1.68
    ma
    1.67
    Activations Density 0.001%

    No Known Activations