© 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. 129620
    Prev
    Next
    INDEX
    Explanations

    SC-FDMA networks

    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
     
    -0.06
    พิเศษ
    -0.06
     specially
    -0.06
     খুবই
    -0.06
    特別
    -0.06
    特殊
    -0.06
     особы
    -0.06
    forth
    -0.06
     প্রত্যেকের
    -0.05
    пециа
    -0.05
    POSITIVE LOGITS
    ாவும்
    0.08
     또한
    0.07
     também
    0.07
     también
    0.07
     također
    0.07
    াও
    0.07
    🏢
    0.07
     طرق
    0.06
     webhook
    0.06
    ⛓
    0.06
    Activations Density 0.002%

    No Known Activations