© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9359
    Prev
    Next
    INDEX
    Explanations

    joints and arthritis

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

    joints and arthritis

    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_40_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
    腹
    0.44
    邺
    0.42
    linetype
    0.40
     SBT
    0.39
    回路
    0.39
     шокола
    0.38
     ブラ
    0.37
    脳
    0.37
    顔
    0.37
    巧克力
    0.37
    POSITIVE LOGITS
     joints
    1.99
     Joints
    1.95
     joint
    1.93
    关节
    1.91
    Joint
    1.88
    joints
    1.85
     Joint
    1.83
    joint
    1.82
     arthritis
    1.77
     arth
    1.73
    Activations Density 0.227%

    No Known Activations