© 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. 128530
    Prev
    Next
    INDEX
    Explanations

    triazine

    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
    窣
    -0.06
     optionally
    -0.06
    его
    -0.06
    㸸
    -0.06
    ive
    -0.06
     কির
    -0.06
    yx
    -0.06
    ソファ
    -0.06
     інші
    -0.06
     všechny
    -0.06
    POSITIVE LOGITS
    कात
    0.07
    というか
    0.06
     avec
    0.06
    的
    0.06
     使用
    0.06
     faced
    0.06
     dengan
    0.06
    ുകയാണ്
    0.06
     ſ
    0.05
     setores
    0.05
    Activations Density 0.057%

    No Known Activations