© 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. 119897
    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
     utilizamos
    -0.07
     வளர்ச்சி
    -0.06
     elegance
    -0.06
     innerhalb
    -0.06
     εφαρ
    -0.06
     Zusatz
    -0.06
     داخل
    -0.06
     внутри
    -0.06
     sophistication
    -0.05
     colspan
    -0.05
    POSITIVE LOGITS
    相关
    0.07
    acquisto
    0.07
    相關
    0.07
    相关的
    0.07
    hältnis
    0.06
    mainly
    0.06
    fron
    0.06
     jud
    0.06
    uero
    0.06
    期限
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.