© 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. 117575
    Prev
    Next
    INDEX
    Explanations

    artery types

    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
     Complaint
    -0.07
    নকে
    -0.07
     scrotum
    -0.07
    falcon
    -0.06
     पोर्टल
    -0.06
     गिलास
    -0.06
     complaint
    -0.06
     خارج
    -0.06
    colnames
    -0.06
    Complaint
    -0.06
    POSITIVE LOGITS
     vivere
    0.06
     composed
    0.06
    ความ
    0.06
     trei
    0.06
    fueled
    0.06
     Miami
    0.06
    ല്ലാം
    0.05
    dominated
    0.05
     末
    0.05
     reviving
    0.05
    Activations Density 0.035%

    No Known Activations