© 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. 118623
    Prev
    Next
    INDEX
    Explanations

    cold sores, herpesviruses, virus reactivation, temps

    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
    :`
    -0.06
     Since
    -0.06
    াস্থ
    -0.06
     questão
    -0.06
    Fract
    -0.06
     Mosque
    -0.05
     Offic
    -0.05
     affirmation
    -0.05
     niemand
    -0.05
     inhom
    -0.05
    POSITIVE LOGITS
    加热
    0.06
     sceptical
    0.06
     genet
    0.06
     Heated
    0.06
     samedi
    0.06
    awsze
    0.06
    askets
    0.06
    uters
    0.06
    产品的
    0.06
    报警
    0.06
    Activations Density 0.005%

    No Known Activations