© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43287
    Prev
    Next
    INDEX
    Explanations

    translucent materials and underserved communities

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

    The neuron detects mentions of see-through material descriptors (e.g. “translucent,” “transparent”).

    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
     kemer
    -3.25
     spesifik
    -3.03
    Ꮏ
    -2.98
     praktis
    -2.92
     opsi
    -2.91
     risiko
    -2.91
     kredi
    -2.86
    ╿
    -2.86
     organik
    -2.84
     konsep
    -2.83
    POSITIVE LOGITS
    神
    2.92
    $
    2.86
    pecabe
    2.78
    "
    2.77
    鹮
    2.72
    頻繁
    2.69
    튿
    2.64
    ところが
    2.61
     feiner
    2.56
    还是很
    2.48
    Activations Density 0.015%

    No Known Activations