© 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. 10519
    Prev
    Next
    INDEX
    Explanations

    semicolon or parenthesis

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

    loop indices and statement terminators

    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
    經營
    0.41
    那种
    0.40
     مز
    0.40
     جنت
    0.39
     Ausstattung
    0.39
     ممال
    0.39
    嵓
    0.39
     কিছুটা
    0.38
    糜
    0.38
    LIE
    0.38
    POSITIVE LOGITS
     ;
    0.62
     i
    0.62
    isConnected
    0.54
     she
    0.52
     it
    0.50
    ;;)
    0.48
    ;;
    0.48
     !
    0.45
     I
    0.44
     It
    0.43
    Activations Density 0.010%

    No Known Activations