© 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. 31968
    Prev
    Next
    INDEX
    Explanations

    syntax sugar and shorthands

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

    concise syntax or shorthand

    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
     गांव
    0.46
    你們
    0.46
    國家
    0.44
     outskirts
    0.44
    停車
    0.44
     tiver
    0.42
    糧
    0.42
     Lleg
    0.41
    屋
    0.41
     grassland
    0.41
    POSITIVE LOGITS
     syntax
    0.98
     Syntax
    0.87
     specifying
    0.85
    语法
    0.83
    Syntax
    0.78
     syntactic
    0.76
     shorthand
    0.72
     implicitly
    0.70
     specify
    0.66
     explicitly
    0.66
    Activations Density 0.039%

    No Known Activations