© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 109423
    Prev
    Next
    INDEX
    Explanations

    friction and lubrication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Amen
    0.47
     الزد
    0.42
    紥
    0.41
    葲
    0.40
    ฐ
    0.40
     정사각형
    0.39
    fora
    0.39
    坆
    0.39
    agedy
    0.39
     നെറ്റ്‌വർ
    0.39
    POSITIVE LOGITS
     friction
    2.36
     Friction
    2.14
    friction
    2.00
     frictional
    1.98
    摩擦
    1.95
     frictions
    1.85
     frictionless
    1.75
     fric
    1.70
     lubric
    1.50
     lubrication
    1.45
    Activations Density 0.035%

    No Known Activations