© 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. 119376
    Prev
    Next
    INDEX
    Explanations

    best way, treatment, part

    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
     همیشه
    -0.07
     항상
    -0.07
     siempre
    -0.07
     ไม่มี
    -0.07
     всегда
    -0.07
     is
    -0.06
     هذا
    -0.06
     அவர்களின்
    -0.06
    JIM
    -0.06
     由于
    -0.06
    POSITIVE LOGITS
     other
    0.06
    تابع
    0.06
    :"
    0.05
    other
    0.05
     interconnected
    0.05
    示
    0.05
    van
    0.05
    名前
    0.05
    rop
    0.05
    dual
    0.05
    Activations Density 0.021%

    No Known Activations