© 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. 10-GEMMASCOPE-RES-131K
    7. 59832
    Prev
    Next
    INDEX
    Explanations

    System.out

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

    The neuron fires on the identifier “out” (e.g. the “out” in System.out.println).

    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
    翆
    -2.19
    込んだ
    -2.13
     in
    -2.02
    癀
    -1.99
    crania
    -1.99
    蕻
    -1.95
     вышел
    -1.92
    wickshire
    -1.89
    ändler
    -1.88
    তথ্য
    -1.88
    POSITIVE LOGITS
    .
    2.98
    *
    2.78
    “
    2.28
    '
    2.20
    \
    1.99
    鱨
    1.86
    ~
    1.81
    ㄴ
    1.81
    this
    1.77
     vertes
    1.77
    Activations Density 0.003%

    No Known Activations