© 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. 117822
    Prev
    Next
    INDEX
    Explanations

    fire incidents and emergency response

    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
     EMEA
    -0.07
    尴尬
    -0.06
     ఇంకా
    -0.06
    ั่ง
    -0.06
    when
    -0.06
     отра
    -0.06
    xg
    -0.06
    ྨ
    -0.06
     washers
    -0.06
     এর
    -0.06
    POSITIVE LOGITS
     bọn
    0.06
     אחרי
    0.06
     CONCLUSION
    0.06
     улица
    0.06
     CLIENT
    0.06
    firetruck
    0.06
    ちなみに
    0.06
     cumple
    0.06
    出席
    0.06
     juf
    0.06
    Activations Density 0.036%

    No Known Activations