© 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. 34-GEMMASCOPE-RES-131K
    7. 65861
    Prev
    Next
    INDEX
    Explanations

    representative works

    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_34/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
    进度
    -0.83
    endola
    -0.69
    (":
    -0.68
    ストーリー
    -0.66
     картинки
    -0.66
    ்கள
    -0.65
     Redaktion
    -0.64
     Verlet
    -0.64
    intios
    -0.63
    ilie
    -0.62
    POSITIVE LOGITS
     works
    5.88
    works
    4.22
     Works
    4.16
    作品
    4.03
    Works
    4.00
     work
    3.61
     WORKS
    3.56
     obras
    3.50
    WORKS
    3.47
     Werke
    2.89
    Activations Density 0.122%

    No Known Activations