© 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. 1803
    Prev
    Next
    INDEX
    Explanations

    discourse markers

    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
    ラー
    0.84
    および
    0.84
    網站
    0.83
    ism
    0.81
    ”،
    0.79
    リ
    0.79
     представлены
    0.78
    íduos
    0.78
     сообщает
    0.76
    ัติ
    0.76
    POSITIVE LOGITS
     subconsciously
    1.37
     biraz
    1.32
     Biraz
    1.29
     unspoken
    1.22
     overkill
    1.18
     kinda
    1.17
     그냥
    1.15
    <unused779>
    1.13
     quirks
    1.11
     이것
    1.11
    Activations Density 1.366%

    No Known Activations