© 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. 3919
    Prev
    Next
    INDEX
    Explanations

    harmonization and harmonic concepts

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

    the substring “harmon” in any token.

    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
     sociala
    -3.08
     ของ
    -3.00
    ти
    -2.73
    ﮟ
    -2.69
     Of
    -2.67
    蹰
    -2.67
     berät
    -2.55
     With
    -2.48
    ╿
    -2.48
     Their
    -2.44
    POSITIVE LOGITS
    '
    3.67
    the
    3.28
    n
    3.13
    ar
    3.00
     spezi
    2.81
    {
    2.77
    [
    2.72
     =
    2.61
    輒
    2.36
    ro
    2.28
    Activations Density 0.006%

    No Known Activations