© 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. 129731
    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
     $+$
    -0.06
     admiring
    -0.06
     penetrate
    -0.06
     concerted
    -0.06
    狗狗
    -0.06
     bring
    -0.06
     neglecting
    -0.06
     nö
    -0.06
     tampering
    -0.06
    whitespace
    -0.06
    POSITIVE LOGITS
     biosynthetic
    0.06
     ತಾ
    0.06
    萼
    0.06
     ಒಂದು
    0.06
     इंग्ल
    0.06
     இவற்றை
    0.06
     unglaublich
    0.06
    Prim
    0.06
     evaluation
    0.05
     Kentucky
    0.05
    Activations Density 0.000%

    No Known Activations