© 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. 54132
    Prev
    Next
    INDEX
    Explanations

    include directives

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

    This neuron detects C preprocessor include directives, especially Linux kernel header includes.

    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
    ERSHIP
    -1.18
    orige
    -1.17
     newer
    -1.11
     uye
    -1.11
     latter
    -1.11
     و
    -1.10
     Menü
    -1.09
     Vorgang
    -1.05
     malé
    -1.05
    𝜌
    -1.05
    POSITIVE LOGITS
    ַּ
    1.33
     on
    1.25
     at
    1.16
    ֶּ
    1.16
    BACA
    1.15
     but
    1.13
     and
    1.12
     Günther
    1.09
    这部
    1.09
    Klass
    1.06
    Activations Density 0.018%

    No Known Activations