© 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. 85821
    Prev
    Next
    INDEX
    Explanations

    Section numbers

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

    The neuron never fires on any of these inputs—it doesn’t appear to detect any pattern in the provided 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
    日本的
    -1.80
     机器
    -1.73
     简介
    -1.73
    icône
    -1.70
    ]
    -1.63
    \
    -1.57
     抽象
    -1.55
     环
    -1.52
    pullover
    -1.52
     большую
    -1.48
    POSITIVE LOGITS
     diário
    1.97
    𝟵
    1.73
     --
    1.67
     undang
    1.67
    UNTAS
    1.66
     wszystkich
    1.64
    es
    1.64
     third
    1.60
     Anbau
    1.59
     People
    1.58
    Activations Density 0.018%

    No Known Activations