© 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. 117032
    Prev
    Next
    INDEX
    Explanations

    comparison with controls

    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
    વું
    -0.06
    separate
    -0.06
     separate
    -0.06
     uncanny
    -0.06
     doors
    -0.06
     একটি
    -0.06
     consequence
    -0.06
    িত্র
    -0.06
     Unser
    -0.06
     Everton
    -0.06
    POSITIVE LOGITS
     বিন্দু
    0.06
    dummies
    0.06
     histoires
    0.06
    大好き
    0.06
     numai
    0.06
    的方法
    0.05
     sauf
    0.05
     작동
    0.05
     including
    0.05
    воря
    0.05
    Activations Density 0.021%

    No Known Activations