© 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. 34-GEMMASCOPE-RES-131K
    7. 60805
    Prev
    Next
    INDEX
    Explanations

    printf style formatting

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

    The neuron fires on numeric width specifiers inside printf‐style format strings (e.g. the “%10”, “%9” in format calls).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    サイズの
    -0.73
     Walgreens
    -0.73
     microw
    -0.70
    發現
    -0.69
     [%
    -0.69
    搀
    -0.69
     gondol
    -0.68
    던
    -0.68
    zé
    -0.68
    vents
    -0.68
    POSITIVE LOGITS
     %.
    2.56
    %.
    2.47
    ("%.
    2.14
     {:.
    2.09
    :%.
    1.44
     \%$.
    1.23
    %,
    1.16
     float
    1.00
    :.
    0.91
    float
    0.88
    Activations Density 0.004%

    No Known Activations