© 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. 119453
    Prev
    Next
    INDEX
    Explanations

    complex systems and related theories

    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
    éről
    -0.06
     инвали
    -0.06
     Single
    -0.06
    Single
    -0.06
    cell
    -0.06
     single
    -0.06
     børn
    -0.06
    苗
    -0.06
     любить
    -0.05
     istnie
    -0.05
    POSITIVE LOGITS
     공부
    0.06
     menghad
    0.06
     relato
    0.06
     kịp
    0.06
     سسٹم
    0.06
     coincident
    0.06
    oky
    0.06
     மாசுபாடு
    0.06
    inery
    0.06
    blems
    0.06
    Activations Density 0.008%

    No Known Activations