© 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. 117466
    Prev
    Next
    INDEX
    Explanations

    submitted, argued, admit

    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
    cur
    -0.06
    inf
    -0.05
    োক
    -0.05
     vytvá
    -0.05
    bling
    -0.05
    read
    -0.05
     zuerst
    -0.05
     simply
    -0.05
     Montgomery
    -0.05
    mug
    -0.05
    POSITIVE LOGITS
     fondamentale
    0.07
     आईपीएल
    0.07
     jaaye
    0.06
    🔜
    0.06
     everyone
    0.06
     Jaaye
    0.06
     Adin
    0.06
    全員
    0.06
    队的
    0.06
    principles
    0.06
    Activations Density 0.001%

    No Known Activations