© 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. 117001
    Prev
    Next
    INDEX
    Explanations

    pronouns and titles

    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
     ailing
    -0.06
     gritty
    -0.06
     proprietor
    -0.06
    𝑯
    -0.06
    হিংস
    -0.06
    তাহাদের
    -0.06
     wellknown
    -0.06
     potenciales
    -0.06
     Innen
    -0.06
    Ｒ
    -0.06
    POSITIVE LOGITS
      
    0.10
       
    0.08
    <0xE3>
    0.07
        
    0.07
    、
    0.07
     இருந்தால்
    0.06
     रहीं
    0.06
          
    0.06
    Instead
    0.06
    但
    0.06
    Activations Density 0.074%

    No Known Activations