© 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. 31-GEMMASCOPE-2-RES-262K
    7. 158843
    Prev
    Next
    INDEX
    Explanations

    hobby, exploring, processes, donors, vehicle funds

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

    breaking down concepts

    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_31_width_262k_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
     काळजी
    0.42
     அடு
    0.41
    ayım
    0.39
    は
    0.39
    inkl
    0.39
    ढ
    0.38
     dø
    0.38
     सर्वप्रथम
    0.38
     शंकर
    0.38
    ≡
    0.38
    POSITIVE LOGITS
    жень
    0.46
     acab
    0.43
     asent
    0.43
     effic
    0.42
     pung
    0.42
    拉斯
    0.42
     Wirtschafts
    0.42
     intelig
    0.41
    baarheid
    0.40
    Cxx
    0.40
    Activations Density 0.000%

    No Known Activations