© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2584
    Prev
    Next
    INDEX
    Explanations

    demonyms and geographical 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_13_width_65k_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
     sillä
    1.44
    豸
    1.36
    ékek
    1.33
    ത്തിലാണ്
    1.32
    თ
    1.30
    잼
    1.29
    வாத
    1.26
    ouwen
    1.16
    ríklad
    1.15
    사실
    1.14
    POSITIVE LOGITS
    <0xF3>
    1.87
       
    1.58
     anto
    1.53
     х
    1.47
    һ
    1.46
        
    1.45
     Го
    1.45
     оригина
    1.44
     )}$
    1.44
    ℠
    1.44
    Activations Density 0.047%

    No Known Activations