© 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. 42729
    Prev
    Next
    INDEX
    Explanations

    reference condition or starting point

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

    This neuron specifically activates on occurrences of the word “baseline.”

    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
    ↵↵
    -2.59
     The
    -2.58
     to
    -2.56
     ถ้า
    -2.25
     unſ
    -2.20
    茑
    -2.19
    鑁
    -2.11
    饧
    -2.09
     we
    -2.08
     ‘’
    -2.08
    POSITIVE LOGITS
    This
    2.83
    ༷
    2.47
    時間も
    2.41
    You
    2.36
    Several
    2.31
    準備
    2.27
     أيض
    2.27
    That
    2.22
    Before
    2.22
    After
    2.19
    Activations Density 0.002%

    No Known Activations