© 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. 120666
    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
    步
    -0.07
    это
    -0.07
    𝘴
    -0.06
    するのが
    -0.06
     enforcing
    -0.06
     그것
    -0.06
     Emily
    -0.06
    six
    -0.06
     mendapatkan
    -0.06
     acela
    -0.06
    POSITIVE LOGITS
     WHEN
    0.06
     not
    0.06
    原有
    0.06
     не
    0.06
     अस्थ
    0.06
     фильме
    0.06
    ),
    0.06
    PlatformToolset
    0.06
     reference
    0.06
     referenced
    0.06
    Activations Density 0.000%

    No Known Activations