© 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. 118515
    Prev
    Next
    INDEX
    Explanations

    MEMORANDUM, DECISION, CERTIORARI, APPEAL

    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
     in
    -0.07
     प्रत्येक
    -0.06
     tentunya
    -0.06
     svaki
    -0.06
    每个
    -0.06
    4
    -0.06
    など
    -0.06
    ↵↵↵
    -0.06
     ótimo
    -0.06
    !
    -0.06
    POSITIVE LOGITS
     ৩
    0.07
     ৭
    0.07
     the
    0.07
     Comrade
    0.07
     and
    0.06
     spontaneous
    0.06
     geographical
    0.06
     व
    0.06
     ১২
    0.06
     ৫
    0.06
    Activations Density 0.009%

    No Known Activations