© 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. 13-GEMMASCOPE-2-RES-16K
    7. 16354
    Prev
    Next
    INDEX
    Explanations

    numbers and currency in calculations

    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
     запро
    1.02
     وف
    0.98
     особен
    0.88
     выпла
    0.85
     представитель
    0.84
     сни
    0.84
    蒯
    0.83
    试验
    0.83
     сле
    0.82
     рано
    0.82
    POSITIVE LOGITS
     endowed
    0.78
     tackled
    0.78
     interrelated
    0.77
    រយៈ
    0.75
     eradicated
    0.74
     اربع
    0.74
    enthal
    0.74
    OCH
    0.74
     partner
    0.74
    mitted
    0.74
    Activations Density 0.072%

    No Known Activations