© 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. 118170
    Prev
    Next
    INDEX
    Explanations

    kidnapping and abduction contexts

    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
     препят
    -0.06
     URL
    -0.06
    不安
    -0.06
     security
    -0.06
     নিরাপত্ত
    -0.06
     中
    -0.06
     sabotage
    -0.06
    URL
    -0.06
     不
    -0.06
     blockage
    -0.06
    POSITIVE LOGITS
     that
    0.07
    普通の
    0.06
     average
    0.06
     adultos
    0.06
     nineties
    0.06
     ordinary
    0.06
    ৃদ্ধ
    0.06
     appropriateness
    0.06
     biraz
    0.06
     noviembre
    0.06
    Activations Density 0.007%

    No Known Activations