© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65348
    Prev
    Next
    INDEX
    Explanations

    compliment and complimentary

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

    The neuron detects occurrences of the root “compliment” (e.g. “compliments,” “complimentary”).

    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
    磲
    -3.19
    }$
    -3.11
     nurture
    -2.59
     maintain
    -2.48
     поскольку
    -2.47
     renew
    -2.47
    mpagne
    -2.45
    ⎽
    -2.42
    血糖
    -2.42
     solchen
    -2.39
    POSITIVE LOGITS
    さてさて
    2.80
    さあ
    2.78
    酲
    2.72
    ではでは
    2.70
    さぁ
    2.59
    the
    2.58
    というわけで
    2.56
    そういえば
    2.55
    珰
    2.53
    灕
    2.52
    Activations Density 0.003%

    No Known Activations