© 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. 86908
    Prev
    Next
    INDEX
    Explanations

    graphene and composites

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

    2D materials in scientific literature, including graphene, phosphorus, and other layered materials.

    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
    同比
    -1.30
    0
    -1.30
    感じです
    -1.25
    ters
    -1.23
     («
    -1.23
     dürfte
    -1.23
     Zaw
    -1.22
     daripada
    -1.21
    战斗力
    -1.21
    doesn
    -1.20
    POSITIVE LOGITS
     pedimos
    1.41
     beliebt
    1.34
     Naciones
    1.30
    玊
    1.26
    YEAR
    1.25
    createObject
    1.23
    怍
    1.21
     nasz
    1.20
     naszym
    1.19
    ชื่อ
    1.15
    Activations Density 0.096%

    No Known Activations