© 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. 130703
    Prev
    Next
    INDEX
    Explanations

    control parameters

    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
    行動
    -0.07
     objectives
    -0.07
     उद्देश्य
    -0.06
    行动
    -0.06
     of
    -0.06
     PLANS
    -0.06
    निय
    -0.06
    としては
    -0.06
     controllo
    -0.06
    zis
    -0.06
    POSITIVE LOGITS
     odio
    0.06
     enum
    0.06
    损害
    0.06
    Укра
    0.06
    uszt
    0.06
    കുന്ന
    0.06
     chromatic
    0.06
     воспользова
    0.06
     Audio
    0.06
    undaki
    0.06
    Activations Density 0.008%

    No Known Activations