© 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. 119262
    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
    はこの
    -0.08
     понадоби
    -0.07
     இதற்கு
    -0.07
     seemed
    -0.07
     bringing
    -0.07
     इस
    -0.06
     গেরিলাদের
    -0.06
     came
    -0.06
     만드는
    -0.06
     must
    -0.06
    POSITIVE LOGITS
     inappropriate
    0.07
     congratulate
    0.06
     Resultados
    0.06
     proximité
    0.06
     работода
    0.06
    히려
    0.06
     vaisseau
    0.06
    optical
    0.06
    attutto
    0.06
     삽니다
    0.06
    Activations Density 0.000%

    No Known Activations