© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2086
    Prev
    Next
    INDEX
    Explanations

    punctuation after words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     Букмекердик
    1.75
     Казіно
    1.74
     Букмекерлер
    1.66
     그죠
    1.61
    <unused1421>
    1.55
     그러면은
    1.54
    <unused1465>
    1.47
     Спорттук
    1.46
    <unused875>
    1.45
    <unused1463>
    1.45
    POSITIVE LOGITS
    ,
    7.29
    ،
    5.69
    ，
    5.51
    ,(
    4.96
    ,…
    4.81
    、
    4.72
    ,...
    4.68
    ,*
    4.68
    ,,
    4.52
    ,[
    4.51
    Activations Density 16.957%

    No Known Activations