© 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. 117412
    Prev
    Next
    INDEX
    Explanations

    geographical features and locations

    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
     bijna
    -0.06
     絶対
    -0.06
     быст
    -0.06
    插件
    -0.05
     APIs
    -0.05
     प्रतिनि
    -0.05
    anking
    -0.05
     cepat
    -0.05
     brzo
    -0.05
    Hostname
    -0.05
    POSITIVE LOGITS
     sebelum
    0.07
     before
    0.07
     بال
    0.06
     colaboración
    0.06
     Himalayan
    0.06
     disregarding
    0.06
     BEFORE
    0.06
     keeping
    0.06
    submenu
    0.06
     Pence
    0.06
    Activations Density 0.014%

    No Known Activations