© 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. 161816
    Prev
    Next
    INDEX
    Explanations

    reducing or alternatives

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

    descriptive modifiers and their contexts

    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
     Pythag
    0.48
    不说
    0.47
    ebvre
    0.46
    م
    0.46
     personel
    0.46
    एनजी
    0.46
     kunne
    0.46
     wọn
    0.46
    출
    0.46
    maschinen
    0.45
    POSITIVE LOGITS
     orice
    0.52
    或者
    0.43
    ‌.
    0.42
    или
    0.40
     sólida
    0.40
     acetonitrile
    0.39
     چکا
    0.39
    يرين
    0.39
     または
    0.39
    =!
    0.39
    Activations Density 0.000%

    No Known Activations