© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 390
    Prev
    Next
    INDEX
    Explanations

    relative clauses or descriptors

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

    that work

    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_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
    ↵
    0.21
    ↵↵
    0.20
     parentheses
    0.20
     (.
    0.19
     )
    0.18
     ($
    0.17
     (--
    0.17
     $(
    0.17
     zodat
    0.17
     [(
    0.17
    POSITIVE LOGITS
     we
    0.19
    soever
    0.17
     কিনা
    0.16
    स्तों
    0.16
    不仅
    0.15
    asyarakat
    0.15
    ched
    0.14
    мога
    0.14
    人们
    0.14
     використову
    0.14
    Activations Density 1.122%

    No Known Activations