© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3535
    Prev
    Next
    INDEX
    Explanations

    torque and torsion

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

    Torvin, PyTorch, µTorrent

    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_53_width_65k_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
     ფუნქ
    0.42
     Inequal
    0.40
    函數
    0.40
     Clustering
    0.39
     mamm
    0.39
    函数
    0.38
     irradi
    0.38
    稃
    0.38
    징
    0.37
    廬
    0.37
    POSITIVE LOGITS
     torsion
    2.50
     tors
    2.42
     tor
    2.38
     Tor
    2.34
    Tor
    2.31
     TOR
    2.30
     тор
    2.19
    tors
    2.17
     Torque
    2.13
     torque
    2.11
    Activations Density 0.015%

    No Known Activations