© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 117116
    Prev
    Next
    INDEX
    Explanations

    convolutional neural network

    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
     além
    -0.07
    また
    -0.07
     Ezra
    -0.06
    側に
    -0.06
     열심히
    -0.06
     علاوه
    -0.05
     ispod
    -0.05
     to
    -0.05
     से
    -0.05
     manned
    -0.05
    POSITIVE LOGITS
    ϊ
    0.06
     января
    0.06
    облада
    0.06
    ractions
    0.06
    blusas
    0.06
     olursa
    0.05
    কব
    0.05
     பகிர்ந்து
    0.05
     consulte
    0.05
     ಸಂಖ್ಯ
    0.05
    Activations Density 0.001%

    No Known Activations