© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36588
    Prev
    Next
    INDEX
    Explanations

    introductory words

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

    The neuron detects the sequence “};” that marks the end of a JavaScript code block or statement.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    postolic
    -1.15
    nemia
    -1.09
     بتاريخ
    -1.05
    licante
    -1.01
     bereiken
    -0.98
    Източници
    -0.94
    peel
    -0.93
     jurk
    -0.93
    Conclusión
    -0.92
     Rptr
    -0.92
    POSITIVE LOGITS
     of
    1.05
     they
    1.05
    จึง
    1.02
     with
    1.01
    Any
    0.93
     они
    0.89
     azonban
    0.87
     if
    0.86
     and
    0.85
    他们
    0.84
    Activations Density 0.000%

    No Known Activations