© 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. 98633
    Prev
    Next
    INDEX
    Explanations

    programming output `<<`

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

    The main thing this neuron does is detect uses of the C++ output stream “cout.”

    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
     you
    -2.03
    ategorie
    -1.85
    broj
    -1.81
    Tracce
    -1.81
     durch
    -1.80
    聍
    -1.80
     PUSTAKA
    -1.78
    lgari
    -1.77
    lahir
    -1.77
    rozum
    -1.73
    POSITIVE LOGITS
    '
    2.38
    “
    2.19
    ti
    2.00
    ar
    1.99
    an
    1.97
    ate
    1.92
    (
    1.89
    慙
    1.87
    er
    1.85
    –
    1.85
    Activations Density 0.000%

    No Known Activations