© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128204
    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
     is
    -0.08
     specific
    -0.07
    特定
    -0.07
     or
    -0.07
     was
    -0.07
     bestimmte
    -0.07
    specific
    -0.07
     как
    -0.07
     may
    -0.07
     bestimmten
    -0.07
    POSITIVE LOGITS
     सम्प
    0.06
     ដែល
    0.06
     hordes
    0.06
     hapless
    0.06
     starving
    0.06
     infr
    0.06
     depleted
    0.06
     starved
    0.06
     disobey
    0.06
     naquele
    0.05
    Activations Density 0.000%

    No Known Activations