© 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. 117351
    Prev
    Next
    INDEX
    Explanations

    potentially burning, safely store, possible affects

    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
     seluruh
    -0.07
     বিরোধী
    -0.06
     conhecida
    -0.06
    ก่อน
    -0.06
     शिल्
    -0.06
     conhecido
    -0.06
     bastante
    -0.06
     hơn
    -0.06
     каких
    -0.06
     известный
    -0.06
    POSITIVE LOGITS
     identique
    0.07
    ើញ
    0.07
     identical
    0.06
     olyan
    0.06
    definite
    0.06
     "#
    0.06
    回忆
    0.06
     such
    0.06
     போன்ற
    0.06
     включа
    0.06
    Activations Density 0.013%

    No Known Activations