© 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. 22-GEMMASCOPE-RES-131K
    7. 70956
    Prev
    Next
    INDEX
    Explanations

    conclusion or end

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

    The neuron fires on closing punctuation markers (e.g. a period or the “},” sequence) that signal the end of a sentence or code block.

    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
     mengucap
    -1.27
     Quaternion
    -1.12
     mépris
    -1.11
    ☽
    -1.04
     expliqué
    -1.01
     Desember
    -1.00
    #(
    -0.99
     начала
    -0.98
     réaliste
    -0.97
    asted
    -0.97
    POSITIVE LOGITS
     and
    1.21
    return
    1.07
     concludes
    1.00
     schließlich
    0.94
    CONCLUSION
    0.94
    你和
    0.92
     letzt
    0.91
    בס
    0.91
     sicherlich
    0.91
     concluding
    0.90
    Activations Density 0.000%

    No Known Activations