© 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. 117491
    Prev
    Next
    INDEX
    Explanations

    newly diagnosed medical conditions

    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
     چهار
    -0.07
     راست
    -0.07
    非常に
    -0.06
     bahkan
    -0.06
     väldigt
    -0.06
     extremely
    -0.06
     ಬಹಳ
    -0.06
     очень
    -0.06
     даже
    -0.06
    成像
    -0.06
    POSITIVE LOGITS
    выми
    0.06
     nuevo
    0.06
     novità
    0.06
     nuevos
    0.06
     everything
    0.06
     температур
    0.06
     нового
    0.06
     any
    0.06
     innovating
    0.06
     newly
    0.06
    Activations Density 0.017%

    No Known Activations