© 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. 17-GEMMASCOPE-2-RES-16K
    7. 929
    Prev
    Next
    INDEX
    Explanations

    `sed` command substitution syntax `s/ / /`

    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_17_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
    非常
    0.85
     شئ
    0.84
     또
    0.82
    もっと
    0.81
     находиться
    0.81
    また
    0.79
    さらに
    0.79
    Something
    0.79
     Something
    0.78
    Ре
    0.77
    POSITIVE LOGITS
    =(
    1.73
    =
    1.70
    ="+
    1.68
    =\
    1.61
    ={
    1.58
    =[
    1.57
    =.
    1.48
    ="
    1.47
    =/
    1.45
    ={(
    1.44
    Activations Density 0.068%

    No Known Activations