© 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. 117511
    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
    although
    -0.07
    缺乏
    -0.07
     despite
    -0.07
     nonostante
    -0.06
     धन
    -0.06
     young
    -0.06
     বেশিরভাগ
    -0.06
    颊
    -0.06
     প্রচুর
    -0.06
     even
    -0.06
    POSITIVE LOGITS
    forever
    0.06
    如果要
    0.06
     طلب
    0.05
     énon
    0.05
     extraordinaire
    0.05
    Если
    0.05
    tochrome
    0.05
     отказаться
    0.05
     فاذا
    0.05
     kako
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.