© 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. 129202
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ,
    -0.07
     factory
    -0.06
    м
    -0.06
     Factory
    -0.05
     also
    -0.05
     завод
    -0.05
     doğru
    -0.05
    以上の
    -0.05
    の写真
    -0.05
     также
    -0.05
    POSITIVE LOGITS
     Cardiovascular
    0.07
     cardiovascular
    0.07
    বিদেশ
    0.06
    
    0.06
     وابسته
    0.06
    からです
    0.06
    になって
    0.06
     voicemail
    0.06
    selectTable
    0.06
     hierarchy
    0.06
    Activations Density 0.000%

    No Known Activations