© 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. 120176
    Prev
    Next
    INDEX
    Explanations

    list items or data entries

    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
    不同
    -0.07
    このような
    -0.06
     playbook
    -0.06
     clergy
    -0.06
    Shared
    -0.06
    同じ
    -0.06
     Shared
    -0.06
     स्लाइड
    -0.06
    ikult
    -0.06
     leaked
    -0.06
    POSITIVE LOGITS
     また
    0.07
     সিভি
    0.06
    また
    0.06
    rets
    0.06
    examen
    0.06
     enclose
    0.06
    它们
    0.05
     escudo
    0.05
    rats
    0.05
     wrapped
    0.05
    Activations Density 0.001%

    No Known Activations