© 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. 111889
    Prev
    Next
    INDEX
    Explanations

    molecular pattern

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

    scientific and technical terminology related to electronic components, medical conditions, and technical standards.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects long, multi‐part technical or scientific terms—especially compound names (e.g. chemical, biological, or engineering jargon) and acronyms.

    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
    still
    -1.64
     znaleźć
    -1.50
     使用
    -1.43
     vœ
    -1.42
     still
    -1.41
     folgendes
    -1.41
    пление
    -1.31
    、
    -1.30
     kupić
    -1.30
    push
    -1.30
    POSITIVE LOGITS
     that
    2.03
     (
    1.87
     Перейти
    1.79
    创始
    1.48
    datable
    1.45
    xvi
    1.38
    xvii
    1.38
    čnega
    1.37
    osoba
    1.34
    cún
    1.33
    Activations Density 0.765%

    No Known Activations