© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130927
    Prev
    Next
    INDEX
    Explanations

    X and Y alike

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -2.64
    其他的
    -1.69
     nasze
    -1.68
    别的
    -1.59
    ⚢
    -1.58
     jedną
    -1.54
     используя
    -1.49
     or
    -1.49
    ございました
    -1.48
    asiswa
    -1.45
    POSITIVE LOGITS
    ؛
    1.94
    '
    1.87
    n
    1.86
     are
    1.77
    The
    1.73
    r
    1.67
    l
    1.63
     acredita
    1.63
    是
    1.62
    k
    1.61
    Activations Density 0.003%

    No Known Activations