© 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. 119530
    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
     просто
    -0.07
    跟你
    -0.06
     অ্যাস
    -0.06
     ग्रीन
    -0.06
    ரம்
    -0.06
     semplicemente
    -0.06
    붉
    -0.06
     그냥
    -0.06
     каждому
    -0.06
     simply
    -0.06
    POSITIVE LOGITS
     on
    0.06
     wiele
    0.06
     இன்னொரு
    0.06
     ZERO
    0.06
     biggest
    0.06
     flank
    0.06
     intermittently
    0.06
     realistically
    0.06
    pril
    0.06
     bords
    0.06
    Activations Density 0.000%

    No Known Activations