© 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. 128959
    Prev
    Next
    INDEX
    Explanations

    condensed instructions or enumerations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     नाटक
    -0.06
     rued
    -0.06
    akaan
    -0.06
     மொத்தம்
    -0.05
     Rotating
    -0.05
     Fredrik
    -0.05
    替代
    -0.05
    Eff
    -0.05
     रहीं
    -0.05
    Specific
    -0.05
    POSITIVE LOGITS
     endless
    0.07
     dacă
    0.07
     اذا
    0.06
     oleh
    0.06
     nếu
    0.06
     sẽ
    0.06
     implements
    0.06
     kalau
    0.06
     if
    0.06
     هذا
    0.06
    Activations Density 0.001%

    No Known Activations