© 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. 130022
    Prev
    Next
    INDEX
    Explanations

    PATCH, @@, Canada Wood, triphosphate

    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
     this
    -0.08
     এই
    -0.07
     هذا
    -0.07
    极其
    -0.07
     inqui
    -0.07
    这个
    -0.07
    mateurs
    -0.07
     این
    -0.07
    लेबल
    -0.07
     acknowledging
    -0.07
    POSITIVE LOGITS
     apenas
    0.07
    4
    0.07
    3
    0.06
    .
    0.06
    Sometimes
    0.06
    2
    0.06
    Nature
    0.06
    Fort
    0.05
     berbentuk
    0.05
     called
    0.05
    Activations Density 0.001%

    No Known Activations