© 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-16K
    7. 8594
    Prev
    Next
    INDEX
    Explanations

    political office or territory or ice

    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_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
    &*
    1.17
    esses
    1.13
     serta
    1.07
    uglify
    1.05
    并在
    1.05
    ipio
    1.04
    üng
    1.02
    &$
    1.02
    threads
    1.02
    ijk
    1.01
    POSITIVE LOGITS
     barley
    1.19
    传感器
    1.14
     hoja
    1.12
    ட்டர்
    1.10
     crou
    1.09
    zana
    1.09
     musicale
    1.06
     athletic
    1.05
     normalement
    1.04
     sensor
    1.04
    Activations Density 0.000%

    No Known Activations