© 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. 120279
    Prev
    Next
    INDEX
    Explanations

    disease severity routes virulence

    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
     ligados
    -0.07
     πριν
    -0.06
     correction
    -0.06
     bisogno
    -0.06
     corrections
    -0.06
    continue
    -0.06
     मार्क्स
    -0.06
     continuando
    -0.06
     χρει
    -0.06
    Hobbies
    -0.06
    POSITIVE LOGITS
     facilitated
    0.06
     cytotoxic
    0.06
     virulence
    0.06
     was
    0.06
     lethal
    0.06
     delivers
    0.06
     compared
    0.06
     அனைத்து
    0.06
     zab
    0.06
     governed
    0.06
    Activations Density 0.015%

    No Known Activations