© 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. 129679
    Prev
    Next
    INDEX
    Explanations

    This neuron flags highly technical mathematical or signal-processing jargon—especially names and acronyms of transforms (e.g. “Discrete Hartley transform,” “DFT,” “DHT”) and closely related terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mathematical transforms and accounting

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    जे
    -1.02
     italiane
    -0.98
     eléctricas
    -0.92
     without
    -0.92
     percentage
    -0.90
     combinations
    -0.90
     if
    -0.90
     or
    -0.89
    सत
    -0.89
     most
    -0.86
    POSITIVE LOGITS
     saia
    1.07
    lüsse
    1.05
     dourado
    1.02
     Selon
    1.02
     remé
    1.00
    лата
    0.98
    下载附件
    0.98
    Ɣ
    0.97
     borboleta
    0.97
    ונ
    0.94
    Activations Density 0.002%

    No Known Activations