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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 479
    Prev
    Next
    INDEX
    Explanations

    India and Pakistan rural contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
    ಸ್ಕೊ
    1.20
     பாபிலோ
    1.15
    பிலோ
    1.08
     கல்லற
    1.08
    Kyle
    1.05
     claire
    1.00
     Kyle
    0.99
    疃
    0.99
     দেখুনঃ
    0.99
     ভিয়েতনাম
    0.97
    POSITIVE LOGITS
     Maharashtra
    2.58
     Gujarat
    2.51
     Uttar
    2.41
     Haryana
    2.39
     Karnataka
    2.39
     Rajasthan
    2.38
     Delhi
    2.36
     Jharkhand
    2.35
     Andhra
    2.34
    Maharashtra
    2.34
    Activations Density 1.843%

    No Known Activations