© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118997
    Prev
    Next
    INDEX
    Explanations

    asking a question

    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
     gemeente
    -0.06
    これで
    -0.06
     Corpo
    -0.06
     collaboratively
    -0.06
     Wast
    -0.06
     समझौते
    -0.06
    🏫
    -0.06
    services
    -0.06
    💥
    -0.06
     giữ
    -0.06
    POSITIVE LOGITS
     cidad
    0.07
     시민
    0.07
    ंद्व
    0.06
     வாய
    0.06
     직원
    0.06
     la
    0.06
     업무
    0.06
     incapable
    0.06
    ადი
    0.06
     reda
    0.06
    Activations Density 0.005%

    No Known Activations