© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69466
    Prev
    Next
    INDEX
    Explanations

    Eigen library and eigenvalues

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

    The neuron fires on occurrences of the term “Eigen” (e.g. in library names, identifiers, or include guards).

    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
    骉
    -2.63
    l
    -2.63
    袮
    -2.44
     使っ
    -2.33
    ᠂
    -2.30
    桕
    -2.28
     That
    -2.27
     When
    -2.23
    ↵
    -2.17
     them
    -2.16
    POSITIVE LOGITS
     himmel
    3.30
    橚
    3.22
     kosme
    2.89
     keramik
    2.88
    豨
    2.86
    一八
    2.83
    materi
    2.83
    鉕
    2.80
    驁
    2.77
     drau
    2.72
    Activations Density 0.004%

    No Known Activations