© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 52266
    Prev
    Next
    INDEX
    Explanations

    swing motion or action

    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_65k_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
    摊
    0.44
     কুক
    0.41
     근무
    0.41
     Multiply
    0.41
    ত্ব
    0.39
     epidermis
    0.39
     cuticle
    0.38
    Mapping
    0.38
    ított
    0.38
    鳖
    0.38
    POSITIVE LOGITS
     swinging
    2.14
     swing
    2.13
     Swing
    1.96
     swung
    1.94
     swings
    1.88
    Swing
    1.88
     Swinging
    1.80
    swing
    1.75
     pendulum
    1.38
     pend
    1.01
    Activations Density 0.024%

    No Known Activations