© 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. 28971
    Prev
    Next
    INDEX
    Explanations

    lust and lustrous words

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

    The neuron strongly activates on tokens containing the substring “lust” (e.g. lust, lustrous, wanderlust, bloodlusting).

    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
    
    -2.70
    摃
    -2.66
    哢
    -2.47
    鉺
    -2.47
    睒
    -2.45
     всѣ
    -2.44
    鷂
    -2.42
    曏
    -2.41
    盌
    -2.39
    豨
    -2.38
    POSITIVE LOGITS
    ’
    3.38
    .
    3.19
    }
    2.69
    '
    2.47
     of
    2.16
    人也
    2.08
    o
    2.06
     треть
    2.03
    <i>
    2.03
    ↵
    1.94
    Activations Density 0.001%

    No Known Activations