© 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. 3564
    Prev
    Next
    INDEX
    Explanations

    far apart / distancia entre

    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
     persons
    1.05
     вами
    1.04
     ex
    1.02
     or
    0.99
     субъек
    0.98
     VIP
    0.94
    /
    0.93
     please
    0.92
     %
    0.90
    network
    0.90
    POSITIVE LOGITS
     analisi
    1.59
     ricerche
    1.57
     história
    1.54
     illustrazione
    1.52
     সঞ্জীবনী
    1.51
     menyelesaikan
    1.50
     menawarkan
    1.49
     mencapai
    1.49
     memulai
    1.49
     réalise
    1.46
    Activations Density 0.214%

    No Known Activations