© 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. 39621
    Prev
    Next
    INDEX
    Explanations

    "readonly" in code declarations

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

    This neuron detects the C# keyword “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
     to
    -2.38
     ถ้า
    -2.34
    <td>
    -2.31
    ⚋
    -2.28
    镠
    -2.25
     Если
    -2.14
    躄
    -2.05
    𖥧
    -2.05
    at
    -2.03
     货
    -2.03
    POSITIVE LOGITS
    ll
    2.27
    you
    2.13
    돕
    2.09
    ls
    2.08
    A
    2.03
    Ⴀ
    2.00
    _
    1.98
    the
    1.98
    Ἢ
    1.98
    it
    1.97
    Activations Density 0.002%

    No Known Activations