© 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. 117462
    Prev
    Next
    INDEX
    Explanations

    URL links

    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
     that
    -0.07
     ça
    -0.06
    これが
    -0.06
    கூ
    -0.06
     एक
    -0.06
     বস্ত্র
    -0.06
     पनीर
    -0.06
     ranging
    -0.06
     Energ
    -0.06
    Performance
    -0.05
    POSITIVE LOGITS
     guides
    0.06
     paralelas
    0.06
     Lease
    0.06
     Whip
    0.06
     understandings
    0.06
     многие
    0.05
     தண்ணீ
    0.05
     IDs
    0.05
     ayrıca
    0.05
     المسافه
    0.05
    Activations Density 0.003%

    No Known Activations