© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43904
    Prev
    Next
    INDEX
    Explanations

    cities and capitals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     ग्रामीणों
    0.53
     वृक्ष
    0.48
     ditches
    0.45
     дере
    0.45
     woodlands
    0.44
     landowners
    0.43
     खेतों
    0.42
    朗
    0.42
     Blueberry
    0.42
     woodland
    0.42
    POSITIVE LOGITS
     city
    0.90
     capital
    0.89
     cidade
    0.85
     शहर
    0.84
     столи
    0.84
    city
    0.84
     cities
    0.83
     राजधानी
    0.82
    capital
    0.80
     capitals
    0.80
    Activations Density 0.105%

    No Known Activations