© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2888
    Prev
    Next
    INDEX
    Explanations

    discussing or explaining

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

    The neuron is strongly activated by punctuation marks (commas, periods, parentheses, etc.), effectively detecting sentence-boundary and separators in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    应用
    -0.94
    readAs
    -0.93
     skriver
    -0.92
    addField
    -0.90
     dukungan
    -0.90
    ndrome
    -0.89
    doi
    -0.88
     wrote
    -0.87
    mmt
    -0.86
     katika
    -0.86
    POSITIVE LOGITS
     glú
    1.14
     discussing
    1.07
     explaining
    1.06
     Gespräch
    1.06
     midway
    1.06
     momentarily
    1.05
     sitting
    1.04
     noticeably
    1.03
     conversation
    1.02
    していて
    1.02
    Activations Density 0.032%

    No Known Activations