© 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. 20032
    Prev
    Next
    INDEX
    Explanations

    material or technical compound terms

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

    The neuron fires strongly on concrete technical nouns denoting materials, components, or devices in scientific and engineering contexts.

    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
     irmã
    -1.52
     senhora
    -1.50
    胖子
    -1.48
    𖥦
    -1.48
    Какво
    -1.48
     their
    -1.47
    Inggris
    -1.40
    ılmış
    -1.40
    Neden
    -1.39
    Açık
    -1.38
    POSITIVE LOGITS
     combinatie
    1.31
     outcast
    1.25
    ها
    1.24
     valeurs
    1.23
    <i>
    1.23
    未必
    1.22
    F
    1.20
    ウェ
    1.19
     даже
    1.17
    <h3>
    1.16
    Activations Density 0.679%

    No Known Activations