© 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. 120207
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    exclude
    -0.07
    ONLY
    -0.07
    Exclude
    -0.06
    另一种
    -0.06
     موتور
    -0.06
     phenomenal
    -0.06
     foundational
    -0.06
     overtly
    -0.06
    Oops
    -0.06
    গতের
    -0.06
    POSITIVE LOGITS
     do
    0.06
    
    0.06
     are
    0.06
     traduire
    0.06
    combined
    0.06
     തമ്മ
    0.06
    <blockquote>
    0.06
     trois
    0.06
     jednotliv
    0.06
     लक्षात
    0.05
    Activations Density 0.008%

    No Known Activations