© 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. 20433
    Prev
    Next
    INDEX
    Explanations

    programming objects

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

    This neuron detects CamelCase programming identifiers (class, type, or API names) in 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_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
     pamoja
    -1.16
    邢
    -1.14
    即是
    -1.13
    ować
    -1.13
    приклад
    -1.11
     \&
    -1.11
    ли
    -1.10
     choisis
    -1.09
     kawaida
    -1.09
    )、
    -1.09
    POSITIVE LOGITS
     to
    1.60
     recensioni
    1.39
     jadx
    1.33
    Nguyên
    1.28
    ENIA
    1.26
     Scritto
    1.25
    やすく
    1.24
    一惊
    1.23
     July
    1.23
     uParam
    1.22
    Activations Density 0.070%

    No Known Activations