© 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. 11707
    Prev
    Next
    INDEX
    Explanations

    formatting text and data

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

    the word "formatting" in programming and technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of the word “formatting.”

    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
    y
    -3.28
    是
    -3.05
    en
    -2.95
     With
    -2.80
    is
    -2.77
    他
    -2.72
    它
    -2.70
    er
    -2.69
    s
    -2.63
    的
    -2.52
    POSITIVE LOGITS
    朏
    3.33
    踌
    2.84
    聼
    2.72
    昞
    2.69
    贔
    2.64
    ハロウィン
    2.59
    辚
    2.59
    艄
    2.56
    柺
    2.55
    サイズは
    2.52
    Activations Density 0.002%

    No Known Activations