© 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. 128723
    Prev
    Next
    INDEX
    Explanations

    biotinylated or conjugated labels

    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
     중에
    -0.06
    中でも
    -0.06
    茥
    -0.06
    som
    -0.06
    uleiro
    -0.06
    க்களை
    -0.06
    㦣
    -0.05
     filóso
    -0.05
     জনক
    -0.05
    error
    -0.05
    POSITIVE LOGITS
    你自己
    0.07
    要么
    0.06
     one
    0.06
     divorce
    0.06
    Sobre
    0.06
     gute
    0.06
     WOMEN
    0.06
    离婚
    0.06
    หนึ่ง
    0.06
     タイヤ
    0.06
    Activations Density 0.003%

    No Known Activations