© 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. 120037
    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
     वगैरह
    -0.08
     perhaps
    -0.07
    Perhaps
    -0.06
     during
    -0.06
     wakati
    -0.06
    perhaps
    -0.06
     Perhaps
    -0.06
     and
    -0.06
     নামের
    -0.06
     Wor
    -0.06
    POSITIVE LOGITS
     Padilla
    0.07
     únicamente
    0.06
     García
    0.06
     rotund
    0.06
     decidió
    0.06
     uniquement
    0.06
     우리는
    0.06
     уровнем
    0.06
    gift
    0.06
     যেভাবে
    0.06
    Activations Density 0.000%

    No Known Activations