© 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. 117360
    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
    exceptions
    -0.06
    それぞれの
    -0.06
    requent
    -0.06
     admittedly
    -0.05
    чних
    -0.05
     PC
    -0.05
    PC
    -0.05
    ņu
    -0.05
    aikh
    -0.05
     সালের
    -0.05
    POSITIVE LOGITS
     쭉
    0.07
    挀
    0.07
    makt
    0.06
    texttt
    0.06
    स्ती
    0.06
    🤍
    0.06
     continu
    0.06
     María
    0.06
     coordinador
    0.06
     surv
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.