© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2109
    Prev
    Next
    INDEX
    Explanations

    pairs like keep supporting, with financial, have same

    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_16_width_65k_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
     rejoindre
    0.52
     région
    0.51
     zudem
    0.49
     nữ
    0.49
     Studenten
    0.49
     bedeut
    0.48
    ầy
    0.47
    靚
    0.47
     bauen
    0.46
    សូម
    0.46
    POSITIVE LOGITS
    TT
    0.54
    ्यु
    0.51
    ATE
    0.50
    UTE
    0.50
    ylvania
    0.50
    ppage
    0.50
    TTLE
    0.49
    IBLE
    0.48
    ONES
    0.48
    IO
    0.47
    Activations Density 0.000%

    No Known Activations