© 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. 130293
    Prev
    Next
    INDEX
    Explanations

    packaging bottles

    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
     सेट
    -0.06
    ど
    -0.06
     UN
    -0.06
     दो
    -0.06
     ice
    -0.06
    utc
    -0.06
    Putin
    -0.06
     दावा
    -0.06
     основа
    -0.05
     extenso
    -0.05
    POSITIVE LOGITS
    Storing
    0.07
     påver
    0.06
     brewery
    0.06
     beeinfl
    0.06
     Distillery
    0.06
     प्रतिनिधित्व
    0.06
    Ultimately
    0.06
    Visualize
    0.06
     whiskey
    0.06
     মিয়া
    0.06
    Activations Density 0.052%

    No Known Activations