© 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. 1558
    Prev
    Next
    INDEX
    Explanations

    is followed by adverb or article

    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
    it
    1.30
    is
    1.26
    en
    1.22
    -
    1.22
    ies
    1.21
    at
    1.21
    I
    1.18
    if
    1.17
    ar
    1.13
    sh
    1.12
    POSITIVE LOGITS
    <unused1224>
    1.94
     termed
    1.90
     considerado
    1.87
     comprised
    1.86
     considerada
    1.83
    采用了
    1.80
    <unused1189>
    1.79
     characterized
    1.78
    <unused1185>
    1.77
    采用
    1.77
    Activations Density 2.895%

    No Known Activations