© 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. 119359
    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
     meiner
    -0.07
    тивность
    -0.07
     siquiera
    -0.07
     seit
    -0.06
     move
    -0.06
    こういう
    -0.06
     هذا
    -0.06
     તા
    -0.06
     solchen
    -0.06
     حتى
    -0.06
    POSITIVE LOGITS
     environmental
    0.06
    発見
    0.05
     economic
    0.05
     stedet
    0.05
     discovery
    0.05
     maintaining
    0.05
     مجال
    0.05
     ईडी
    0.05
    ofer
    0.05
     non
    0.05
    Activations Density 0.000%

    No Known Activations