© 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. 119863
    Prev
    Next
    INDEX
    Explanations

    directing and controlling

    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
     their
    -0.07
    headed
    -0.07
    他們的
    -0.07
    director
    -0.06
    他们的
    -0.06
    校长
    -0.06
     njihov
    -0.06
     তাহাদের
    -0.06
    总经理
    -0.06
     zorgt
    -0.06
    POSITIVE LOGITS
     गहन
    0.06
     simulated
    0.06
     subordinate
    0.06
     constructed
    0.06
     všet
    0.06
     DB
    0.06
     confeder
    0.06
     quartet
    0.05
     tất
    0.05
     어렵
    0.05
    Activations Density 0.062%

    No Known Activations