© 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. 11638
    Prev
    Next
    INDEX
    Explanations

    ugly descriptions

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

    The neuron activates on the adjective “ugly” (and its direct mentions) whenever it appears in text.

    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
    訁
    -2.80
    剮
    -2.69
     But
    -2.58
    菝
    -2.31
    
    -2.22
    にほんブログ村
    -2.19
     แต่
    -2.19
    
    -2.16
    ).
    -2.14
     noti
    -2.11
    POSITIVE LOGITS
    或
    2.52
    s
    2.39
    or
    2.28
    0
    2.25
     fashioned
    2.13
    🪬
    2.13
    utterstock
    2.08
    也非常
    2.06
    劼
    2.05
    榑
    2.02
    Activations Density 0.002%

    No Known Activations