© 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. 114407
    Prev
    Next
    INDEX
    Explanations

    commemorate, trade, capacity

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

    status updates

    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
     mengatasi
    0.50
    )=(
    0.46
    EXIST
    0.46
     større
    0.45
    REG
    0.44
     impulsive
    0.44
     Daytona
    0.43
     revê
    0.43
     =(
    0.43
    )$\
    0.42
    POSITIVE LOGITS
     liczba
    0.52
     Jews
    0.49
     commemorate
    0.48
    ulis
    0.48
    oths
    0.46
    etian
    0.44
    zado
    0.44
     trade
    0.43
     रही
    0.43
     писатель
    0.43
    Activations Density 0.000%

    No Known Activations