© 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. 119593
    Prev
    Next
    INDEX
    Explanations

    official bodies or roles

    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
     prerogative
    -0.06
     pressing
    -0.06
    pected
    -0.06
    ংকা
    -0.05
     espec
    -0.05
    窜
    -0.05
    ｅ
    -0.05
     боле
    -0.05
    thrust
    -0.05
    깽
    -0.05
    POSITIVE LOGITS
    だけで
    0.07
    只是
    0.07
    可能是
    0.07
    翮
    0.07
     individual
    0.06
     sozinho
    0.06
     standalone
    0.06
    象征
    0.06
     smaller
    0.06
     कोणता
    0.06
    Activations Density 0.001%

    No Known Activations