© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 16360
    Prev
    Next
    INDEX
    Explanations

    structural strength and materials

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

    material strength and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    艺术家
    0.55
    hiddenMap
    0.55
    PhotoButton
    0.54
     tumble
    0.51
    cameraId
    0.50
     कैमरा
    0.49
    段时间
    0.49
    电
    0.49
    电器
    0.49
    onedDateTime
    0.49
    POSITIVE LOGITS
     brittle
    0.85
     geotechnical
    0.84
     strength
    0.82
     stresses
    0.82
     Strength
    0.80
     Structural
    0.80
     structural
    0.80
     Reinforced
    0.79
    structural
    0.73
    strength
    0.73
    Activations Density 0.420%

    No Known Activations