© 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. 129650
    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
     осно
    -0.06
     grunds
    -0.06
     supremacist
    -0.06
    This
    -0.05
     This
    -0.05
    american
    -0.05
    EntityFramework
    -0.05
     menyebut
    -0.05
    <sup>
    -0.05
     THE
    -0.05
    POSITIVE LOGITS
     without
    0.06
     χωρίς
    0.06
     без
    0.06
     uten
    0.06
    acles
    0.06
     слегка
    0.06
    itiva
    0.06
     zonder
    0.06
     utan
    0.06
     kissed
    0.06
    Activations Density 0.000%

    No Known Activations