© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 131033
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and formulas

    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
     이게
    -0.06
    這是
    -0.06
    と同じ
    -0.06
     talvez
    -0.06
    可能是
    -0.06
     same
    -0.06
     misc
    -0.06
    总是
    -0.06
     stessa
    -0.06
    也许
    -0.06
    POSITIVE LOGITS
     an
    0.07
     irrevoc
    0.07
     the
    0.07
     your
    0.07
     on
    0.06
     their
    0.06
     a
    0.06
     Predict
    0.06
     চন্দ্র
    0.06
     நிய
    0.06
    Activations Density 0.004%

    No Known Activations