© 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. 38736
    Prev
    Next
    INDEX
    Explanations

    resource management and allocation

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

    The neuron fires on code identifiers for the Orchid library and its resource classes (i.e. tokens like “Orchid,” “orchid,” “Resource,” and “resource”).

    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
    鉺
    -2.72
    s
    -2.66
    錾
    -2.59
    ſſel
    -2.58
    鑁
    -2.56
    廨
    -2.55
    珰
    -2.52
    鲞
    -2.52
     produkter
    -2.48
    鬭
    -2.48
    POSITIVE LOGITS
     \
    3.11
     And
    2.94
     Importantly
    2.73
     
    2.70
     Additionally
    2.63
     Undoubtedly
    2.58
    ar
    2.56
     Typically
    2.56
     Roughly
    2.55
     is
    2.48
    Activations Density 0.012%

    No Known Activations