© 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. 116989
    Prev
    Next
    INDEX
    Explanations

    MultiGraph and critical

    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
     denne
    -0.07
    Ꞌ
    -0.06
     échanges
    -0.06
    成り立つ
    -0.06
     बीमारी
    -0.06
    更加
    -0.06
    每月
    -0.06
     लगभग
    -0.06
     qualsiasi
    -0.06
     केवल
    -0.06
    POSITIVE LOGITS
     ক্ষমতার
    0.06
     নিয়েও
    0.06
     промо
    0.05
    そのまま
    0.05
     থেকেও
    0.05
     ઉ
    0.05
     مشاهده
    0.05
    uxi
    0.05
    RQ
    0.05
    ikut
    0.05
    Activations Density 0.001%

    No Known Activations