© 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. 129667
    Prev
    Next
    INDEX
    Explanations

    Plaintiff, Defendant, Petitioner

    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
     comprenant
    -0.06
     circumstances
    -0.06
     socalled
    -0.06
     ausdr
    -0.06
     toprak
    -0.05
     केक
    -0.05
    大切な
    -0.05
     wealthy
    -0.05
     However
    -0.05
     explicitly
    -0.05
    POSITIVE LOGITS
     cũng
    0.08
     zonder
    0.07
     también
    0.07
     also
    0.07
     также
    0.07
     без
    0.07
     بدون
    0.07
     senza
    0.07
     whose
    0.07
     모두
    0.07
    Activations Density 0.002%

    No Known Activations