© 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. 117440
    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
    没有
    -0.07
    提供
    -0.06
     weniger
    -0.06
    その
    -0.06
    減少
    -0.06
    整个
    -0.06
     없
    -0.05
     variable
    -0.05
    FG
    -0.05
    取代
    -0.05
    POSITIVE LOGITS
     ആദ്യ
    0.07
     pierws
    0.07
     perpetually
    0.07
     charmed
    0.06
    🎩
    0.06
     cleverly
    0.06
     यानी
    0.06
     anyways
    0.06
     gewonnen
    0.06
     पांच
    0.06
    Activations Density 0.000%

    No Known Activations