© 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. 130548
    Prev
    Next
    INDEX
    Explanations

    radiation transport, MC dose, effective dose

    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
     күн
    -0.07
    NYC
    -0.07
     ежеднев
    -0.07
     täglich
    -0.07
    週末
    -0.06
     corrupt
    -0.06
    städter
    -0.06
     Vj
    -0.06
    prett
    -0.06
     ежедневно
    -0.06
    POSITIVE LOGITS
     phenomenon
    0.08
     pertinent
    0.08
     phenomena
    0.07
     fenomeno
    0.06
    哪里
    0.06
     ()
    0.06
     parent
    0.06
     anaknya
    0.06
     অবশ্য
    0.06
     dinyatakan
    0.06
    Activations Density 0.007%

    No Known Activations