© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118644
    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
     weiteren
    -0.07
    weiter
    -0.07
     efet
    -0.06
     manière
    -0.06
     இறு
    -0.06
     viennent
    -0.06
    native
    -0.06
     prostu
    -0.06
     weitere
    -0.06
     further
    -0.06
    POSITIVE LOGITS
    這種
    0.07
     pamph
    0.06
     neither
    0.06
     except
    0.06
    这种
    0.06
     both
    0.06
     zowel
    0.05
     normalerweise
    0.05
    除去
    0.05
    除
    0.05
    Activations Density 0.000%

    No Known Activations