© 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. 120216
    Prev
    Next
    INDEX
    Explanations

    master suite or bath

    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
     bude
    -0.07
     будет
    -0.07
     kvůli
    -0.06
    ここ
    -0.06
    饯
    -0.06
     отдыха
    -0.06
     टूर
    -0.06
     кожен
    -0.06
    调度
    -0.06
    iseren
    -0.06
    POSITIVE LOGITS
    vendo
    0.06
    男女
    0.06
    ⭐
    0.06
     improved
    0.06
     having
    0.05
     adultery
    0.05
     வரை
    0.05
     elliptic
    0.05
     সরাসরি
    0.05
    cleaned
    0.05
    Activations Density 0.006%

    No Known Activations