© 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. 169349
    Prev
    Next
    INDEX
    Explanations

    Hochzeit, Wedding, kız, wisdom

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

    universe size

    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
    is
    0.50
    t
    0.49
    i
    0.47
    o
    0.45
     introduced
    0.45
    ----------------
    0.44
    ugeot
    0.44
    as
    0.44
     defer
    0.42
     afforded
    0.42
    POSITIVE LOGITS
     kız
    0.51
     Hochzeit
    0.50
     sabiduría
    0.45
    甃
    0.44
    Wedding
    0.44
    hipster
    0.43
    ិត
    0.43
     কন্যা
    0.43
     Dach
    0.42
    民國
    0.42
    Activations Density 0.003%

    No Known Activations