© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72569
    Prev
    Next
    INDEX
    Explanations

    intensifier followed by adjective

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

    The neuron fires on adverbs that express degree or intensity—especially comparative and superlative modifiers like “more,” “very,” and “less.”

    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
    做一个
    -1.70
    汌
    -1.64
    邻居
    -1.56
    ighed
    -1.54
    取决
    -1.53
    偁
    -1.51
    开玩笑
    -1.50
    Ꮠ
    -1.49
    图为
    -1.49
     レスト
    -1.49
    POSITIVE LOGITS
    7
    2.75
    9
    2.41
    3
    2.38
    6
    2.34
    5
    2.33
    8
    2.28
    4
    2.17
    2
    2.11
    </b>
    2.02
    1
    1.58
    Activations Density 0.016%

    No Known Activations