© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85978
    Prev
    Next
    INDEX
    Explanations

    variable interpolation

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

    The neuron is detecting string‐format specifiers (especially percent “%” tokens and related format placeholders) in code or templates.

    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
     znaleźć
    -1.66
    </h5>
    -1.46
    Antecedentes
    -1.35
     Jangan
    -1.34
    我们
    -1.33
     ordinaria
    -1.32
     ถ้า
    -1.32
     cruda
    -1.27
    Примеча
    -1.25
    Коммента
    -1.25
    POSITIVE LOGITS
     "
    1.80
     who
    1.68
     of
    1.64
     "...
    1.55
    "...
    1.52
     However
    1.45
     those
    1.43
     tačiau
    1.41
     ''
    1.41
    "
    1.37
    Activations Density 0.028%

    No Known Activations