© 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. 61354
    Prev
    Next
    INDEX
    Explanations

    programming constructs and builder pattern

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

    The neuron fires on programming identifiers that start with a capital letter—i.e. class/constructor names or other PascalCase tokens 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_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
     in
    -2.67
     on
    -2.36
     by
    -1.89
     was
    -1.79
     de
    -1.69
    ৄ
    -1.67
     at
    -1.62
     =
    -1.59
     en
    -1.59
    佉
    -1.55
    POSITIVE LOGITS
     that
    2.08
    ﺅ
    2.05
    糴
    2.03
    鹟
    1.99
     Choisissez
    1.91
    ︐
    1.82
     parachoque
    1.81
     calzado
    1.79
    蹌
    1.78
    㩒
    1.77
    Activations Density 0.032%

    No Known Activations