© 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. 130376
    Prev
    Next
    INDEX
    Explanations

    shipwreck remains and archaeological debris

    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
     erne
    -0.06
     Herpes
    -0.06
     joyous
    -0.06
     चुप
    -0.06
    ières
    -0.06
    升
    -0.06
    事先
    -0.06
     slight
    -0.06
     trays
    -0.06
     temporarily
    -0.06
    POSITIVE LOGITS
     wreckage
    0.07
    捕捉
    0.07
     поги
    0.07
     decaying
    0.06
     carcass
    0.06
     headlines
    0.06
     प्रयास
    0.06
     погиб
    0.06
    შირ
    0.06
     diferente
    0.06
    Activations Density 0.016%

    No Known Activations