© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7787
    Prev
    Next
    INDEX
    Explanations

    article "The" prefixes

    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_22_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
    anbul
    0.92
     Dass
    0.88
     Alp
    0.87
    虎
    0.87
     MOL
    0.86
    囡
    0.86
     Trab
    0.85
     Nu
    0.84
     Eren
    0.83
     Dif
    0.82
    POSITIVE LOGITS
     The
    2.79
    The
    2.71
    THE
    2.35
     THE
    2.22
    nThe
    1.74
    ザ
    1.53
     ザ
    1.42
     This
    1.39
    This
    1.34
     These
    1.31
    Activations Density 0.092%

    No Known Activations