© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104419
    Prev
    Next
    INDEX
    Explanations

    programming components and libraries

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

    The neuron spots occurrences of library/module/package or header names (imported or included APIs) in source code.

    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
     演出
    -1.20
     dientes
    -1.20
    ſelf
    -1.17
    rostis
    -1.16
     dedos
    -1.16
     vek
    -1.14
    ⇤
    -1.14
     mereka
    -1.13
     papir
    -1.12
    恃
    -1.12
    POSITIVE LOGITS
    がありますが
    1.14
     Cualquier
    1.10
     However
    1.10
    もありますが
    1.09
     можно
    1.05
     is
    1.04
    RESUMEN
    1.04
     можна
    1.03
     करता
    1.02
     Obtén
    1.02
    Activations Density 0.162%

    No Known Activations