© 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. 4733
    Prev
    Next
    INDEX
    Explanations

    character, Silas, bus journey

    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
     jedna
    1.30
     scienze
    1.24
     ciencias
    1.22
     alot
    1.21
    
    1.18
     ludzi
    1.18
     história
    1.17
    𐰆
    1.16
     cosas
    1.16
     pessoas
    1.15
    POSITIVE LOGITS
     will
    2.10
     sẽ
    1.97
    จะ
    1.88
    will
    1.88
     should
    1.86
     would
    1.83
     смогут
    1.81
     сможет
    1.79
     could
    1.79
     poderá
    1.76
    Activations Density 1.176%

    No Known Activations