© 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. 131014
    Prev
    Next
    INDEX
    Explanations

    `as` keyword for aliasing

    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
     fiind
    -0.07
     also
    -0.07
    Also
    -0.06
     বিভিন্ন
    -0.06
     being
    -0.06
    ភេទ
    -0.06
    .
    -0.06
     माझा
    -0.06
    also
    -0.06
     पूर्वानुमान
    -0.06
    POSITIVE LOGITS
    sulph
    0.06
    vish
    0.06
     它
    0.06
     MUL
    0.06
    senal
    0.06
     বিষয়টি
    0.06
     కా
    0.06
    rusty
    0.06
     giphy
    0.05
     इंटरनेशनल
    0.05
    Activations Density 0.019%

    No Known Activations