© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43683
    Prev
    Next
    INDEX
    Explanations

    insertion and cursor position

    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_31_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
     transmutation
    0.43
     kul
    0.39
     polymorphism
    0.39
     tan
    0.38
     পৃষ্ঠপোষ
    0.38
     resolutions
    0.37
     आर्य
    0.37
    醀
    0.37
     resolución
    0.37
     tannins
    0.36
    POSITIVE LOGITS
    Insertion
    0.65
     positioned
    0.62
    Insert
    0.59
     Insertion
    0.58
    插入
    0.57
    Position
    0.56
     insertion
    0.56
    cursor
    0.54
     inserted
    0.54
    Cursor
    0.53
    Activations Density 0.058%

    No Known Activations