© 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. 9048
    Prev
    Next
    INDEX
    Explanations

    very, very intensified adjectives

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

    The neuron fires on doubled intensifier adverbs—specifically “very, very.”

    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
     by
    -1.66
    ⦊
    -1.63
     that
    -1.63
     during
    -1.59
    懺
    -1.58
     keeps
    -1.53
     pollici
    -1.52
     provides
    -1.52
     regularly
    -1.51
    //!
    -1.49
    POSITIVE LOGITS
    ENIE
    1.59
    久しぶり
    1.55
     coloris
    1.52
    撵
    1.47
    İK
    1.47
    证据
    1.46
    走吧
    1.45
     совершенно
    1.45
    τερ
    1.43
     réussir
    1.41
    Activations Density 0.001%

    No Known Activations