© 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
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9635
    Prev
    Next
    INDEX
    Explanations

    US states and their regulations

    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
     Lof
    1.28
     weaver
    1.20
     Erb
    1.17
     weavers
    1.16
    沣
    1.14
    潼
    1.11
     Noy
    1.11
     Moira
    1.09
     秦
    1.09
     Knitting
    1.08
    POSITIVE LOGITS
     Florida
    3.37
    Florida
    3.29
     FLORIDA
    3.19
     Broward
    3.16
     Orlando
    3.02
     Tampa
    2.91
     Everglades
    2.90
     Tallahassee
    2.82
     Miami
    2.80
     florida
    2.78
    Activations Density 0.704%

    No Known Activations