© 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. 120772
    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
     enough
    -0.06
    hala
    -0.06
     overpowered
    -0.06
     wenige
    -0.06
     পায়নি
    -0.06
     inesper
    -0.06
    big
    -0.06
     цього
    -0.05
     laughing
    -0.05
    national
    -0.05
    POSITIVE LOGITS
     និង
    0.07
     difficoltà
    0.06
     becomes
    0.06
     மனதில்
    0.06
     உடலில்
    0.06
    groupBy
    0.06
     வாழ்வில்
    0.06
     difficulty
    0.06
    ﻉ
    0.06
     ভাষায়
    0.06
    Activations Density 0.000%

    No Known Activations