© 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. 68197
    Prev
    Next
    INDEX
    Explanations

    ethical and ethics

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

    The neuron is sharply activated by tokens beginning with “et” – in particular the stems “eth-” (as in ethics/ethical) and “eta” (the Greek‐letter name).

    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
    C
    -2.48
    .;
    -2.34
    u
    -2.30
     wöch
    -2.25
     cercando
    -2.22
     {
    -2.20
    禤
    -2.19
    );
    -2.16
     erzählen
    -2.11
    3
    -2.11
    POSITIVE LOGITS
    ⃙
    2.20
    緇
    2.03
     Tyskland
    1.99
    {
    1.97
     flesta
    1.95
     suced
    1.95
    یین
    1.95
    鷺
    1.94
     gouvernement
    1.92
    '
    1.92
    Activations Density 0.033%

    No Known Activations