© 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. 120120
    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
    に近い
    -0.07
     फ्लावर
    -0.06
    情感
    -0.06
     ومن
    -0.06
    occo
    -0.06
     jednej
    -0.06
     devam
    -0.06
    に適
    -0.06
    자와
    -0.06
     одна
    -0.06
    POSITIVE LOGITS
     you
    0.06
     omitted
    0.06
     collectively
    0.05
     your
    0.05
     always
    0.05
     ذریعہ
    0.05
     circles
    0.05
    出来ます
    0.05
     increasingly
    0.05
     inevitable
    0.05
    Activations Density 0.000%

    No Known Activations