© 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. 66556
    Prev
    Next
    INDEX
    Explanations

    printing and writing output

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

    The neuron detects function calls that output or print text (e.g. print, println, write, printf, fwrite, etc.).

    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
    申し上げます
    -0.84
     than
    -0.83
    cted
    -0.83
     Verkehrs
    -0.82
     its
    -0.82
     formas
    -0.81
    Famous
    -0.81
     jedoch
    -0.80
     hashtag
    -0.80
    cosas
    -0.77
    POSITIVE LOGITS
     napoli
    0.94
     рассказывает
    0.93
     Sancti
    0.93
    uchung
    0.88
    Precious
    0.88
    {}\
    0.87
     直接
    0.85
    "]="
    0.85
    vestimento
    0.85
     roulant
    0.84
    Activations Density 0.023%

    No Known Activations