© 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. 120435
    Prev
    Next
    INDEX
    Explanations

    . followed by key names

    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
     mechanically
    -0.06
     моей
    -0.06
     that
    -0.06
     ,,
    -0.06
     conventionally
    -0.06
     आमच्या
    -0.06
    一般的
    -0.05
     canonically
    -0.05
    fuck
    -0.05
     typical
    -0.05
    POSITIVE LOGITS
     résoudre
    0.07
     якщо
    0.07
     في
    0.07
     समझौ
    0.06
     если
    0.06
     teda
    0.06
     पांच
    0.06
     también
    0.06
     Якщо
    0.06
     عند
    0.06
    Activations Density 0.001%

    No Known Activations