© 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. 43758
    Prev
    Next
    INDEX
    Explanations

    Cyrillic and programming keywords

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

    This neuron activates on nonstandard Unicode characters—letters with diacritics or from non-Latin alphabets.

    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
    Both
    -3.34
    There
    -3.09
    Since
    -2.95
    During
    -2.94
    These
    -2.94
    Using
    -2.88
    After
    -2.80
    Surprisingly
    -2.78
    Before
    -2.75
    Initially
    -2.73
    POSITIVE LOGITS
    圌
    3.00
    𓆏
    2.77
    幛
    2.77
     commenti
    2.73
     batteri
    2.72
    鼍
    2.72
    硨
    2.70
    揠
    2.70
    婠
    2.67
    轳
    2.66
    Activations Density 0.003%

    No Known Activations