© 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. 10-GEMMASCOPE-RES-131K
    7. 130730
    Prev
    Next
    INDEX
    Explanations

    problem followed by trying

    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_10/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
    mados
    -1.68
    ቫ
    -1.63
    gypten
    -1.61
     rằng
    -1.60
    a
    -1.56
     begin
    -1.56
     unruly
    -1.55
     bể
    -1.55
     continue
    -1.48
    mmung
    -1.48
    POSITIVE LOGITS
     to
    1.91
     the
    1.84
    除此之外
    1.60
    所以在
    1.60
    尤其
    1.60
     these
    1.56
    姐妹
    1.55
    所以我
    1.45
    除了
    1.42
     they
    1.37
    Activations Density 0.093%

    No Known Activations