© 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-65K
    7. 2290
    Prev
    Next
    INDEX
    Explanations

    means and methods

    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_65k_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
    喎
    2.05
    న్‌
    1.99
    엷
    1.88
    팎
    1.86
    ớt
    1.83
     tàu
    1.81
    믄
    1.79
    倏
    1.76
    喟
    1.76
     кварта
    1.75
    POSITIVE LOGITS
     individuals
    2.26
     pertaining
    2.14
     данной
    2.05
     данного
    2.02
     alot
    2.01
     Additionally
    2.00
     देखील
    1.97
     utilized
    1.95
     utilizing
    1.94
     utilizes
    1.92
    Activations Density 2.120%

    No Known Activations