© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202261
    Prev
    Next
    INDEX
    Explanations

    city names, locations

    np_acts-logits-general · gemini-2.5-flash-lite

    data CSV file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DONE
    0.52
    anagram
    0.47
    represents
    0.47
    asch
    0.46
    լ
    0.46
    DEAD
    0.46
    리스
    0.46
    squig
    0.45
    ą
    0.45
    ORE
    0.44
    POSITIVE LOGITS
     Gurgaon
    0.49
     Delhi
    0.48
     Ahmedabad
    0.47
     প্রয়োজনে
    0.46
     Kolkata
    0.45
     giọng
    0.43
     Lucknow
    0.43
    শাখ
    0.43
     Gujarat
    0.42
     Kampala
    0.42
    Activations Density 0.001%

    No Known Activations