© 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. 71235
    Prev
    Next
    INDEX
    Explanations

    various technical contexts

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

    The neuron is triggered by PHP code tokens (reserved keywords like namespace, use, class, function, Request, and punctuation such as semicolons).

    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
     Bucure
    -1.23
     castelo
    -1.12
     such
    -1.09
    pandora
    -1.08
    ご存知
    -1.06
     SOBRE
    -1.05
     подобрать
    -1.03
     portu
    -1.02
     maquillage
    -1.01
     собрать
    -1.01
    POSITIVE LOGITS
    क्षण
    1.16
     /\.(
    1.15
    ͎
    1.13
    <bos>
    1.11
     extran
    1.10
    的参数
    1.07
     însă
    1.05
    原始内容存档于
    1.04
     reflexiones
    1.03
     ModelExpression
    1.02
    Activations Density 0.003%

    No Known Activations