© 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. 22134
    Prev
    Next
    INDEX
    Explanations

    EPS, lymphoma, viewModel

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

    The neuron fires whenever it sees the all-caps token “EPS” (as in Encapsulated PostScript or EPSG codes).

    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
    ться
    -3.03
    「
    -2.31
    錞
    -2.30
    でも
    -2.28
    
    -2.16
    </h3>
    -2.11
    猡
    -2.08
    ль
    -2.06
     että
    -2.06
     tenté
    -2.05
    POSITIVE LOGITS
     tne
    2.55
    .”
    2.45
     zmieni
    2.39
    呓
    2.38
    {
    2.38
     wykona
    2.34
    b
    2.30
    il
    2.28
     rozwią
    2.27
    f
    2.27
    Activations Density 0.010%

    No Known Activations