© 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. 34-GEMMASCOPE-RES-131K
    7. 84478
    Prev
    Next
    INDEX
    Explanations

    materials and their properties

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

    The neuron flags domain‐specific technical nouns—especially words naming materials, components, or other specialized substances.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     FormData
    -0.77
     repack
    -0.77
    tokenId
    -0.77
     листь
    -0.71
    Leggi
    -0.69
     със
    -0.69
    ámicas
    -0.68
     engraçadas
    -0.67
    ataan
    -0.67
    шал
    -0.66
    POSITIVE LOGITS
     materials
    6.72
     material
    5.88
     Materials
    4.94
    materials
    4.81
     materiales
    4.59
    material
    4.50
    Materials
    4.44
     Material
    4.19
     MATERIALS
    4.09
    材料
    4.00
    Activations Density 0.186%

    No Known Activations