© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8239
    Prev
    Next
    INDEX
    Explanations

    initialisms and acronyms

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

    acronyms and their completions

    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
    Negative Logits
     userDao
    0.46
     CommandCenter
    0.43
    ⑮
    0.42
    ➎
    0.42
    蓊
    0.42
    வரது
    0.40
     ㅛ
    0.40
    宀
    0.40
     xm
    0.40
     Xe
    0.40
    POSITIVE LOGITS
    CP
    0.46
    CC
    0.46
    ID
    0.46
    DB
    0.46
    IP
    0.45
    CEO
    0.45
    TC
    0.44
    GC
    0.44
    Р
    0.44
    IT
    0.43
    Activations Density 0.228%

    No Known Activations