© 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. 10-GEMMASCOPE-RES-131K
    7. 87226
    Prev
    Next
    INDEX
    Explanations

    curcumin, Peyronie's, Voyager, readFile, Cheyenne, transgressions

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

    The neuron is strongly triggered by occurrences of “cumin” (as in “curcumin”) 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_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
     We
    -2.97
     oleh
    -2.64
    that
    -2.59
     всех
    -2.56
    {
    -2.48
    轳
    -2.48
     dejando
    -2.44
    ING
    -2.42
     тысячи
    -2.42
    by
    -2.41
    POSITIVE LOGITS
    ⦊
    2.59
    镦
    2.52
    罍
    2.48
    𝐖
    2.48
    檍
    2.42
     acteurs
    2.36
    ଝ
    2.33
    都已经
    2.28
    tiously
    2.28
    ﭼ
    2.27
    Activations Density 0.017%

    No Known Activations