© 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. 128375
    Prev
    Next
    INDEX
    Explanations

    exertional headache

    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
     then
    -0.06
     Furthermore
    -0.06
     Moreover
    -0.06
     británico
    -0.06
     Meanwhile
    -0.06
     обычной
    -0.06
     Admittedly
    -0.06
     Then
    -0.06
     Потом
    -0.06
    instead
    -0.06
    POSITIVE LOGITS
     এমনই
    0.07
    ϩ
    0.06
    钧
    0.06
     contacto
    0.06
     cauza
    0.06
     patchy
    0.06
    Contact
    0.05
     সত্ত্বেও
    0.05
    huis
    0.05
    开发
    0.05
    Activations Density 0.416%

    No Known Activations