© 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. 34-GEMMASCOPE-RES-131K
    7. 58738
    Prev
    Next
    INDEX
    Explanations

    MR detection

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

    This neuron spikes on the closing brace “}” of section-ID annotations (e.g. in “{#sec…}”) in document headers.

    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
     such
    -0.98
    ++);
    -0.96
     what
    -0.91
     that
    -0.90
    zookeeper
    -0.90
     needed
    -0.86
     decided
    -0.86
    十二月
    -0.85
     perlu
    -0.85
     potre
    -0.84
    POSITIVE LOGITS
    ходим
    0.84
    Arlington
    0.84
    wens
    0.81
     subscript
    0.79
     آخرین
    0.79
     echte
    0.79
     unselfish
    0.78
    如图
    0.77
     shan
    0.76
    Instead
    0.76
    Activations Density 0.000%

    No Known Activations