© 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. 119597
    Prev
    Next
    INDEX
    Explanations

    past participle

    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
    शरी
    -0.07
     suporte
    -0.06
     Northern
    -0.06
    Northern
    -0.06
     automaton
    -0.06
    ວດ
    -0.06
     autobiography
    -0.06
     cuerpo
    -0.06
     northern
    -0.06
    ❰
    -0.06
    POSITIVE LOGITS
    定义
    0.07
     labors
    0.06
    DEFIN
    0.06
    Definitions
    0.06
     policym
    0.06
    定義
    0.06
     discriminatory
    0.06
    стика
    0.06
     definitions
    0.06
    وث
    0.06
    Activations Density 0.030%

    No Known Activations