© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2325
    Prev
    Next
    INDEX
    Explanations

    a followed by new entities

    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
     somebody
    1.02
     something
    0.99
     it
    0.97
     someth
    0.97
    something
    0.97
    oo
    0.97
     someone
    0.93
     a
    0.92
     quelqu
    0.90
     alot
    0.88
    POSITIVE LOGITS
     지난해
    1.94
     당시
    1.87
     지난
    1.84
     설립
    1.76
     Innovation
    1.68
     groundbreaking
    1.67
     tujuh
    1.66
     چهار
    1.65
     최근
    1.64
     revamped
    1.63
    Activations Density 0.385%

    No Known Activations