© 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. 21702
    Prev
    Next
    INDEX
    Explanations

    special characters and encoding declarations

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

    The neuron flags occurrences of “.h” header filenames (e.g. include or file references ending in “.h”).

    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
    “
    -2.23
    romatic
    -2.05
     bardak
    -1.98
    是
    -1.95
     الموضوع
    -1.94
    breviations
    -1.94
     sia
    -1.91
     بني
    -1.91
     et
    -1.88
    さんは
    -1.88
    POSITIVE LOGITS
     creando
    2.39
     plausible
    2.14
    蠃
    2.02
    璆
    1.99
    ၜ
    1.99
     You
    1.98
    聍
    1.98
     evocative
    1.95
     procurando
    1.95
     generando
    1.95
    Activations Density 0.262%

    No Known Activations