© 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. 74581
    Prev
    Next
    INDEX
    Explanations

    couple of

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

    couple vs couple

    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
    נ
    0.88
    د
    0.87
    י
    0.77
    с
    0.74
    но
    0.72
    स
    0.68
    น
    0.66
    ο
    0.65
    س
    0.65
    𝘯
    0.64
    POSITIVE LOGITS
     früheren
    0.63
    prü
    0.57
    kých
    0.54
    文物
    0.54
    vet
    0.54
    ПА
    0.54
     éve
    0.53
     of
    0.52
    zó
    0.52
    izing
    0.52
    Activations Density 0.017%

    No Known Activations