© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129795
    Prev
    Next
    INDEX
    Explanations

    html title tags

    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
     supports
    -0.06
     على
    -0.06
     Mini
    -0.06
    বাংলাদেশের
    -0.06
     Lorem
    -0.06
     รอง
    -0.06
     にお
    -0.06
    Currently
    -0.06
     sensation
    -0.06
     hypot
    -0.06
    POSITIVE LOGITS
     तो
    0.07
    फेक्ट
    0.06
    asketball
    0.06
     jeśli
    0.06
    ান্ট
    0.06
     fertile
    0.06
     demora
    0.06
     даже
    0.06
    বেশী
    0.05
    arikat
    0.05
    Activations Density 0.017%

    No Known Activations