© 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. 119449
    Prev
    Next
    INDEX
    Explanations

    scientific/technical terms

    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
     contracted
    -0.07
     två
    -0.07
     CONTRACT
    -0.07
     ihrer
    -0.07
     два
    -0.07
     diferenças
    -0.06
     также
    -0.06
     contract
    -0.06
    เกี่ยวกับ
    -0.06
    他們的
    -0.06
    POSITIVE LOGITS
     optimism
    0.07
     pessimism
    0.06
    ageddon
    0.06
    元件
    0.06
     batteries
    0.06
     optimistic
    0.06
     prospects
    0.06
    portrait
    0.06
     viable
    0.06
     architectures
    0.06
    Activations Density 0.002%

    No Known Activations