© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118407
    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
     ordinary
    -0.07
     renowned
    -0.06
    ……..
    -0.06
    _=
    -0.06
    …..
    -0.06
    ..............
    -0.06
     acclaimed
    -0.06
    …)
    -0.06
    ..........
    -0.06
     ingenious
    -0.06
    POSITIVE LOGITS
     αριθ
    0.06
     વિ
    0.06
     оста
    0.06
     Gart
    0.06
    staff
    0.06
    สำหรับ
    0.06
     Equest
    0.06
     zaji
    0.06
     обеспе
    0.06
     Ukraine
    0.06
    Activations Density 0.000%

    No Known Activations