© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13038
    Prev
    Next
    INDEX
    Explanations

    the definite article

    np_acts-logits-general · gemini-2.5-flash-lite

    verb followed by the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     unui
    0.73
    <unused2148>
    0.73
     unor
    0.68
     อะไร
    0.65
    <unused4>
    0.64
     unei
    0.64
    ফটেন
    0.64
     choosing
    0.61
    <unused2156>
    0.59
     ряда
    0.58
    POSITIVE LOGITS
     the
    2.47
    the
    2.25
    The
    1.82
     The
    1.66
    sthe
    1.38
     THE
    1.35
     את
    1.30
     teh
    1.27
     ihe
    1.19
    thed
    1.18
    Activations Density 0.467%

    No Known Activations