© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9120
    Prev
    Next
    INDEX
    Explanations

    Arctic and Antarctic regions

    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
     Modena
    1.21
    邙
    1.16
    陂
    1.13
     वृंदा
    1.10
     Vedic
    1.06
    宓
    1.04
     Middletown
    1.03
    豫
    1.02
     Budapest
    1.01
     Indore
    1.01
    POSITIVE LOGITS
     Alaska
    2.36
    Alaska
    2.33
     Alaskan
    2.18
     Anchorage
    2.09
     Fairbanks
    2.03
     Arctic
    1.96
    Arctic
    1.90
     Yukon
    1.81
     Bering
    1.74
     arctic
    1.71
    Activations Density 0.240%

    No Known Activations