© 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. 116809
    Prev
    Next
    INDEX
    Explanations

    file mode settings

    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
     людям
    -0.07
     स्नान
    -0.06
     htmlentities
    -0.05
     подобных
    -0.05
     konnten
    -0.05
     oameni
    -0.05
    賭
    -0.05
     умень
    -0.05
     når
    -0.05
     น่ะ
    -0.05
    POSITIVE LOGITS
     després
    0.07
     esta
    0.07
     Does
    0.06
     compactly
    0.06
    stability
    0.06
     रखकर
    0.06
     Provide
    0.06
    Surgery
    0.06
    UART
    0.06
     particulière
    0.06
    Activations Density 0.001%

    No Known Activations