© 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. 116369
    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
    work
    -0.06
    <<
    -0.06
    uir
    -0.06
     gü
    -0.05
    に入る
    -0.05
    Ax
    -0.05
    Gr
    -0.05
    tur
    -0.05
     домаш
    -0.05
     permanent
    -0.05
    POSITIVE LOGITS
     seperti
    0.07
     ఒప్ప
    0.07
     بہت
    0.06
     अनुया
    0.06
     wiele
    0.06
     ከፍተኛ
    0.06
    去年
    0.06
     τόσο
    0.06
     FOLLOW
    0.06
     этот
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.