© 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. 66358
    Prev
    Next
    INDEX
    Explanations

    swearing and sworn in

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

    The neuron fires on any inflected form of the verb “swear” (e.g. swears, swore, sworn).

    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
     soared
    -2.59
    ᐕ
    -2.48
     maravillas
    -2.45
    𖤍
    -2.44
    簠
    -2.42
     cuando
    -2.41
     pieles
    -2.39
     accustomed
    -2.39
     conductas
    -2.36
    也会
    -2.34
    POSITIVE LOGITS
    o
    2.48
    </i>
    2.19
     グリーン
    2.08
     raga
    2.00
    off
    1.98
     esat
    1.98
    .
    1.98
     malat
    1.95
    ſtra
    1.93
     Siehe
    1.92
    Activations Density 0.002%

    No Known Activations