© 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. 59
    Prev
    Next
    INDEX
    Explanations

    AML activation

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

    scientific and technical abbreviations and chemical compounds, particularly related to toxins, programming keywords, and medical terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    anud
    -1.73
     econó
    -1.55
     More
    -1.52
     メニュー
    -1.50
    得多
    -1.49
     sikkert
    -1.48
    って感じ
    -1.48
     represents
    -1.47
     showed
    -1.46
     allows
    -1.45
    POSITIVE LOGITS
    and
    2.17
    0
    2.14
    джан
    1.59
    said
    1.59
     if
    1.52
    great
    1.51
    excellent
    1.49
    your
    1.47
    since
    1.47
    have
    1.44
    Activations Density 0.017%

    No Known Activations