© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130628
    Prev
    Next
    INDEX
    Explanations

    `Q:` or mathematical expressions

    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
     관심을
    -0.06
    联合
    -0.06
    Когда
    -0.06
     সাম্প্র
    -0.05
    biased
    -0.05
     ज्यात
    -0.05
     uczni
    -0.05
    ínt
    -0.05
     demonstrable
    -0.05
     mutlaka
    -0.05
    POSITIVE LOGITS
     этой
    0.07
     this
    0.06
     Brown
    0.06
     gentle
    0.06
     Green
    0.06
     Anzahl
    0.06
     Michael
    0.06
     intensely
    0.06
     many
    0.06
     această
    0.06
    Activations Density 0.006%

    No Known Activations