© 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. 1900
    Prev
    Next
    INDEX
    Explanations

    Arabic prepositions and conjunctions

    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
    slf
    0.89
     expenditures
    0.87
     thc
    0.80
     spokes
    0.79
     horns
    0.79
    땀
    0.78
     विविधता
    0.77
     staunch
    0.76
    athers
    0.75
     اله
    0.74
    POSITIVE LOGITS
    ه
    1.23
    ر
    1.19
    e
    1.16
    i
    1.15
    a
    1.05
    กด
    1.00
    oja
    0.99
    enfant
    0.98
    Inicio
    0.98
    る
    0.97
    Activations Density 0.000%

    No Known Activations