© 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. 22-GEMMASCOPE-RES-131K
    7. 84091
    Prev
    Next
    INDEX
    Explanations

    programming declarations

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

    The neuron fires on private‐scope field declarations (i.e. the “private” access modifier, often with “readonly”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     even
    -1.49
    Bagaimana
    -1.36
    Mengapa
    -1.30
    Kenapa
    -1.30
    Spesifikasi
    -1.20
    Hvordan
    -1.18
     даже
    -1.15
    Specifik
    -1.14
     sogar
    -1.13
    ির
    -1.13
    POSITIVE LOGITS
    :_
    1.10
    Ù
    1.09
    <strong>
    1.06
    ___
    1.00
    ‛
    0.99
     już
    0.97
    ][
    0.96
    œ
    0.96
    [,]
    0.95
     vallée
    0.93
    Activations Density 0.011%

    No Known Activations