© 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. 10-GEMMASCOPE-RES-131K
    7. 73352
    Prev
    Next
    INDEX
    Explanations

    academic abstracts and papers

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

    The neuron selectively activates on occurrences of the word “thesis” (and closely related dissertation labels).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    翃
    -3.11
    熥
    -3.11
    
    -3.02
    餿
    -2.92
    ︕
    -2.83
    艄
    -2.78
    軚
    -2.72
     fashioned
    -2.69
    梛
    -2.66
    !"
    -2.64
    POSITIVE LOGITS
    {
    2.80
    There
    2.73
    It
    2.64
    齪
    2.59
    Probably
    2.47
    One
    2.38
    Also
    2.36
    No
    2.34
    Obviously
    2.34
    You
    2.33
    Activations Density 0.007%

    No Known Activations