© 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. 128996
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     bzw
    -0.08
     контроли
    -0.08
     appreciates
    -0.07
     conquered
    -0.06
     및
    -0.06
     또는
    -0.06
     oraz
    -0.06
     युवाओ
    -0.06
     চারটি
    -0.06
    และ
    -0.06
    POSITIVE LOGITS
    之中
    0.07
     methodological
    0.06
     những
    0.06
     misma
    0.06
    如果是
    0.06
     প্রথম
    0.06
    之前
    0.06
     antal
    0.06
     മുൻ
    0.06
     those
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.