© 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. 9976
    Prev
    Next
    INDEX
    Explanations

    completely or 100 percent

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

    auto

    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
     有限
    0.42
    まと
    0.39
    aredPreferences
    0.39
     Considerable
    0.38
    ᱓
    0.38
     KID
    0.38
     accesso
    0.38
    埬
    0.38
     রু
    0.37
     darstellen
    0.36
    POSITIVE LOGITS
    完全
    1.32
     completely
    1.30
     полностью
    1.23
    完全に
    1.23
     entirely
    1.23
     १००
    1.23
     sepenuhnya
    1.22
     completamente
    1.20
     शत
    1.20
     повністю
    1.20
    Activations Density 0.246%

    No Known Activations