© 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. 120170
    Prev
    Next
    INDEX
    Explanations

    Zynga Inc. productions

    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
     kamera
    -0.07
    
    -0.07
    museum
    -0.07
     jaren
    -0.06
    预计
    -0.06
     audiovis
    -0.06
    便利
    -0.06
    combo
    -0.06
     कैमरे
    -0.06
    PHONE
    -0.06
    POSITIVE LOGITS
     accounting
    0.07
    佔
    0.06
     dominate
    0.06
     تولید
    0.06
     reputed
    0.06
     dominating
    0.06
    ්‍
    0.05
     পাকিস্তানী
    0.05
     these
    0.05
     productions
    0.05
    Activations Density 0.004%

    No Known Activations