© 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. 4373
    Prev
    Next
    INDEX
    Explanations

    brands, entities, and concepts

    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
     न
    1.10
     चैप्टर्स
    1.09
     ن
    1.08
    Har
    1.07
    Hay
    1.05
    Herbert
    1.04
     र
    1.04
     بگیر
    1.03
     Conor
    1.02
    Ха
    1.02
    POSITIVE LOGITS
     parameterType
    0.99
    적으로
    0.99
    ibatkan
    0.98
    城乡
    0.97
    ovician
    0.95
    resel
    0.91
    范围内
    0.90
    千年
    0.90
    王国
    0.87
    0.87
    Activations Density 0.015%

    No Known Activations