© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53975
    Prev
    Next
    INDEX
    Explanations

    forces and motion

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

    centrifugal force and circular motion

    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_262k_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
    Жен
    0.42
    缕
    0.40
    订单
    0.40
    温度
    0.40
     toured
    0.39
     térmica
    0.38
    棉
    0.38
    靓
    0.38
     greet
    0.38
     marched
    0.38
    POSITIVE LOGITS
     centrifugal
    0.57
     Gravity
    0.54
     centrifug
    0.49
     hoop
    0.49
     gravity
    0.47
     Circulation
    0.47
     centrifuge
    0.47
     الحلقة
    0.47
     Orbit
    0.46
     Rings
    0.44
    Activations Density 0.015%

    No Known Activations