© 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. 9561
    Prev
    Next
    INDEX
    Explanations

    inspired by

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

    The neuron fires on occurrences of the word “Inspired,” especially in “Inspired by…” phrases.

    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
    N
    -3.19
     '
    -2.69
    S
    -2.61
    2
    -2.41
    但他
    -2.36
    是怎么
    -2.31
    D
    -2.27
    釹
    -2.27
    𖤍
    -2.23
    =
    -2.22
    POSITIVE LOGITS
    .
    4.28
     ถ้า
    2.84
    趼
    2.44
    vantaged
    2.41
    尨
    2.36
    利
    2.27
    ệc
    2.25
    ется
    2.23
     We
    2.23
     兒童
    2.20
    Activations Density 0.007%

    No Known Activations