© 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. 105316
    Prev
    Next
    INDEX
    Explanations

    math syntax and tables

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

    The neuron fires on the vertical-bar “|” tokens used as column separators in ASCII or Markdown-style tables.

    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
     to
    -1.63
     её
    -1.61
     Geset
    -1.59
     we
    -1.58
    渽
    -1.41
     moeili
    -1.41
     podpor
    -1.39
     masculina
    -1.36
     maravilh
    -1.35
    camisetas
    -1.34
    POSITIVE LOGITS
    }
    1.89
    ????????
    1.87
    I
    1.70
    ??????
    1.66
    ☝
    1.62
    }(),
    1.62
    ✨
    1.61
    ?????
    1.59
    ).
    1.59
    👍
    1.59
    Activations Density 0.001%

    No Known Activations