© 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. 12714
    Prev
    Next
    INDEX
    Explanations

    relative clauses

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

    properties, figurative meanings

    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
    ęp
    0.39
    ។
    0.38
    Begriffsklär
    0.37
    jän
    0.37
    alámb
    0.37
    ც
    0.36
     単
    0.36
    ܀
    0.36
    п
    0.36
    АТ
    0.35
    POSITIVE LOGITS
     with
    0.50
     from
    0.47
     ,
    0.47
     eğer
    0.45
     bizim
    0.45
     everytime
    0.44
     TA
    0.44
     Bill
    0.43
     when
    0.42
     lorsque
    0.42
    Activations Density 0.019%

    No Known Activations