© 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. 16917
    Prev
    Next
    INDEX
    Explanations

    punctuation preceding conjunctions or qualifiers

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

    parentheses and commas

    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
    錡
    0.38
     लिहाजा
    0.38
    wort
    0.36
    枱
    0.36
     ወይም
    0.35
     किंवा
    0.35
    át
    0.35
     отличаются
    0.35
    ഗ്ര
    0.34
     እንኳ
    0.34
    POSITIVE LOGITS
    ᱕
    0.41
     बताना
    0.39
    that
    0.39
     firstly
    0.39
     faptul
    0.38
     firsthand
    0.38
     ότι
    0.38
     ج
    0.37
     bahwa
    0.37
     että
    0.37
    Activations Density 0.131%

    No Known Activations