© 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. 70435
    Prev
    Next
    INDEX
    Explanations

    program output printing

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

    The neuron detects occurrences of print statements (calls to `print`) 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_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
    praš
    -1.70
     other
    -1.70
     других
    -1.65
     PUSTAKA
    -1.58
     anderen
    -1.57
    ushchev
    -1.53
    อื่น
    -1.51
    分かります
    -1.48
     donde
    -1.46
     ostavi
    -1.45
    POSITIVE LOGITS
    (
    1.82
    ,
    1.69
    “
    1.63
    ORPG
    1.55
     بلکه
    1.55
     (
    1.50
     umbre
    1.48
    It
    1.48
    𓋼
    1.43
    <<<<
    1.42
    Activations Density 0.007%

    No Known Activations