© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111594
    Prev
    Next
    INDEX
    Explanations

    device formation and control

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

    technical patent language describing methods, apparatus, and processes.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron fires on the dense, formal technical‐specification language you find in patent descriptions—particularly the enumerations of devices, apparatuses, methods, and their specialized components.

    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
     туры
    -1.40
    </b>
    -1.39
     récomp
    -1.38
    🧭
    -1.38
    壅
    -1.35
     både
    -1.34
    裢
    -1.31
     Министер
    -1.29
    👛
    -1.28
    Aler
    -1.27
    POSITIVE LOGITS
     at
    1.73
     with
    1.72
     the
    1.53
     државе
    1.48
    靱
    1.45
     usually
    1.41
     before
    1.40
     here
    1.38
     whose
    1.35
     between
    1.33
    Activations Density 1.154%

    No Known Activations