© 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. 10-GEMMASCOPE-RES-131K
    7. 111494
    Prev
    Next
    INDEX
    Explanations

    etymology of words or concepts

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

    This neuron detects occurrences of the term “etymology” (and its sub‐token fragments) marking etymology section headings or mentions of word origins.

    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
    ஂ
    -2.55
    螓
    -2.05
    柺
    -2.02
    </th>
    -2.02
    </i>
    -1.99
    齜
    -1.96
    StoryboardSegue
    -1.92
    et
    -1.89
     The
    -1.86
    同样的
    -1.84
    POSITIVE LOGITS
    :
    2.00
     \
    1.96
     Título
    1.84
     kurzem
    1.81
     Nuevas
    1.74
     lejos
    1.70
     esbo
    1.68
    quirrel
    1.65
     kalt
    1.64
     Contenido
    1.63
    Activations Density 0.009%

    No Known Activations