© 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. 197352
    Prev
    Next
    INDEX
    Explanations

    options, housing, assisted, spouse

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

    cultural themes and individual expression

    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
     می‌باشد
    0.48
     xinh
    0.47
     Kamis
    0.46
     tadi
    0.46
    :”
    0.44
     ApJ
    0.44
     decrease
    0.43
     Zn
    0.43
     peculiarity
    0.43
     varieg
    0.42
    POSITIVE LOGITS
     Джо
    0.50
    Escol
    0.50
    Chosen
    0.50
    യോഗ
    0.49
    放棄
    0.48
    последствии
    0.47
    И
    0.47
    ере
    0.47
    Де
    0.47
    偿
    0.47
    Activations Density 0.000%

    No Known Activations