© 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. 6829
    Prev
    Next
    INDEX
    Explanations

    confirms, validates, verifies, drying, travel, offline, locally

    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
      
    0.90
    <start_of_image>
    0.82
        
    0.80
       
    0.78
    <0xE0>
    0.76
    <sub>
    0.73
    рель
    0.73
     เขา
    0.71
    ~
    0.71
    vol
    0.70
    POSITIVE LOGITS
     playerId
    0.98
     Turtles
    0.96
    €¦
    0.90
     daffodils
    0.90
     ….
    0.89
     southwestern
    0.88
     (…)
    0.88
     daff
    0.88
    ्युअर
    0.88
    ."[
    0.88
    Activations Density 8.388%

    No Known Activations