© 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. 118249
    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
    itoria
    -0.06
     absorb
    -0.06
     colaborar
    -0.06
     비슷한
    -0.06
    ంటారు
    -0.06
     وف
    -0.06
    सार
    -0.06
    用に
    -0.06
     নন
    -0.06
     આપ
    -0.06
    POSITIVE LOGITS
    その
    0.07
     purported
    0.06
     overly
    0.06
    其
    0.06
     excessively
    0.06
     gagal
    0.06
     मृतकों
    0.06
    legacy
    0.06
     unable
    0.06
    未能
    0.05
    Activations Density 0.000%

    No Known Activations