© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131053
    Prev
    Next
    INDEX
    Explanations

    names often followed by specific suffixes

    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
    ”
    -0.06
     a
    -0.06
     AL
    -0.06
     all
    -0.06
     ill
    -0.06
     tilbake
    -0.06
    无数
    -0.06
    สาร
    -0.06
     including
    -0.05
     व्यापक
    -0.05
    POSITIVE LOGITS
     también
    0.07
     लेना
    0.07
    中でも
    0.07
     использованием
    0.07
     mientras
    0.06
    🔳
    0.06
     também
    0.06
     while
    0.06
     also
    0.06
    しますが
    0.06
    Activations Density 0.076%

    No Known Activations