© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2800
    Prev
    Next
    INDEX
    Explanations

    global geopolitical futures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anecdotal
    0.75
     waterfalls
    0.74
     grammaticality
    0.71
    验
    0.69
     composting
    0.66
     Laravel
    0.65
    সংখ্য
    0.64
    मुख्यमंत्री
    0.64
     সারাদেশে
    0.63
     elektr
    0.63
    POSITIVE LOGITS
     geopol
    1.09
     geopolitical
    0.97
     Cold
    0.89
     Monroe
    0.89
     Diplomacy
    0.89
    냉
    0.88
     diplomacy
    0.85
     дипло
    0.85
     globale
    0.85
    Dipl
    0.85
    Activations Density 0.366%

    No Known Activations