© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117310
    Prev
    Next
    INDEX
    Explanations

    http, https, URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     без
    -0.07
     truy
    -0.06
     ત્રણ
    -0.06
     tylko
    -0.06
     толькі
    -0.06
     കു
    -0.06
     ogranic
    -0.06
     אתה
    -0.06
     Tos
    -0.06
     озна
    -0.06
    POSITIVE LOGITS
    例えば
    0.07
    eller
    0.06
     ^{-
    0.06
     ஏனெ
    0.06
     কেননা
    0.06
     eksempel
    0.06
    よね
    0.06
     miller
    0.06
     एचडी
    0.06
     berita
    0.06
    Activations Density 0.002%

    No Known Activations