© 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. 34-GEMMASCOPE-RES-131K
    7. 83615
    Prev
    Next
    INDEX
    Explanations

    unicode_literals

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

    The neuron fires on occurrences of the identifier “unicode” (e.g. in future imports or Unicode block definitions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Дер
    -0.73
     educación
    -0.69
    ASTNode
    -0.67
     erfaren
    -0.66
    WithIdentifier
    -0.65
    readAs
    -0.65
     אית
    -0.65
     Miley
    -0.65
    MZ
    -0.64
     CELL
    -0.63
    POSITIVE LOGITS
    SIGNATURE
    0.74
    seg
    0.67
    年度
    0.66
     headquartered
    0.65
     asy
    0.63
    esy
    0.63
     дыха
    0.63
     fungi
    0.62
    ostro
    0.61
    hoja
    0.61
    Activations Density 0.071%

    No Known Activations