© 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. 46307
    Prev
    Next
    INDEX
    Explanations

    syntax elements in grammars

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

    parser grammar tokens

    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
    ന്വേഷ
    0.47
     نتی
    0.43
    сур
    0.42
    žia
    0.42
    wią
    0.41
     Maeda
    0.40
    谥
    0.40
     bahkan
    0.39
    irradiated
    0.39
    Residents
    0.39
    POSITIVE LOGITS
     ::=
    0.59
     Parser
    0.58
     Grammar
    0.57
     parser
    0.52
     grammar
    0.49
     Parse
    0.48
     "("
    0.48
    parser
    0.46
    識別
    0.43
     consists
    0.43
    Activations Density 0.003%

    No Known Activations