© 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. 119307
    Prev
    Next
    INDEX
    Explanations

    latitude and longitude

    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
     subsequently
    -0.07
     предостав
    -0.07
     Exploring
    -0.07
     pada
    -0.07
    随后
    -0.07
     continent
    -0.07
     explorers
    -0.07
     Explorer
    -0.07
     onus
    -0.07
     explorer
    -0.06
    POSITIVE LOGITS
     Prod
    0.06
    THERS
    0.06
     रिलेट
    0.05
     azok
    0.05
     গৌর
    0.05
    বর্তী
    0.05
    शेष
    0.05
     পারিবারিক
    0.05
    pros
    0.05
    कर्म
    0.05
    Activations Density 0.005%

    No Known Activations