© 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. 118112
    Prev
    Next
    INDEX
    Explanations

    anti-[medical condition] cancer

    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
     स्नान
    -0.07
     lihat
    -0.07
    বাচক
    -0.07
    }+
    -0.06
     viable
    -0.06
    iero
    -0.06
    noof
    -0.06
     author
    -0.06
    utor
    -0.06
    📥
    -0.06
    POSITIVE LOGITS
    गति
    0.06
     which
    0.06
    自
    0.06
     (
    0.06
     asked
    0.06
    changes
    0.06
     desarrollada
    0.06
    개발
    0.06
     devenue
    0.06
     demander
    0.05
    Activations Density 0.070%

    No Known Activations