© 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. 39265
    Prev
    Next
    INDEX
    Explanations

    luxurious, miraculous, or chaotic adjectives

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

    The neuron detects the word “luxurious” (and closely related ultra-luxury descriptors).

    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
    噲
    -2.75
    ⚌
    -2.50
    蟜
    -2.44
    鉆
    -2.39
    ----------------
    -2.39
     για
    -2.30
    飄
    -2.27
    翆
    -2.27
    为了
    -2.25
    蕷
    -2.25
    POSITIVE LOGITS
    ’
    3.27
    ません
    2.48
    🧌
    2.47
     –
    2.41
     They
    2.27
     "
    2.20
     wants
    2.19
    轳
    2.14
    镡
    2.11
     手绘
    2.09
    Activations Density 0.004%

    No Known Activations