© 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. 10-GEMMASCOPE-RES-131K
    4. 74971
    Prev
    Next
    INDEX
    Explanations

    code structures and file paths

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

    This neuron fires on terms that introduce or load external code or dependencies (e.g. include/import/require/modules/headers).

    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
     новый
    -1.53
    “
    -1.49
     it
    -1.44
     gesunde
    -1.41
     erlä
    -1.40
     بگیرید
    -1.34
    وقال
    -1.34
     новые
    -1.33
    T
    -1.32
     these
    -1.28
    POSITIVE LOGITS
    蛭
    1.40
    囮
    1.38
     for
    1.37
     отметить
    1.36
     MÉXICO
    1.34
     Crear
    1.30
     swee
    1.28
    อื่น
    1.28
    Tere
    1.27
    嚆
    1.25
    Activations Density 0.068%

    No Known Activations