© 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. 128823
    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
    如果
    -0.09
     dacă
    -0.08
     હશે
    -0.07
     jeśli
    -0.07
     если
    -0.07
     어떤
    -0.07
    Jeśli
    -0.06
     underage
    -0.06
    如果是
    -0.06
     إذا
    -0.06
    POSITIVE LOGITS
     kiire
    0.06
     koji
    0.06
     tyto
    0.06
     blank
    0.06
     de
    0.06
     to
    0.06
     जिनका
    0.06
     под
    0.06
    ってみ
    0.06
     transformasi
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.