© 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. 22-GEMMASCOPE-RES-131K
    7. 66716
    Prev
    Next
    INDEX
    Explanations

    academic thesis

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

    The neuron activates on occurrences of “thesis” (and related terms like “dissertation”), marking explicit mentions of academic theses.

    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
    熥
    -2.73
    ︕
    -2.55
    !"
    -2.55
     divent
    -2.45
     ſever
    -2.36
    艄
    -2.36
     unſ
    -2.33
     ваше
    -2.33
    軚
    -2.33
     {
    -2.31
    POSITIVE LOGITS
    ).
    2.78
    {
    2.66
     zusätzlichen
    2.38
    齪
    2.23
    .”
    2.03
     状態
    2.02
    <bos>
    1.95
    Obviously
    1.94
     Schluß
    1.91
    New
    1.91
    Activations Density 0.012%

    No Known Activations