© 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. 91004
    Prev
    Next
    INDEX
    Explanations

    comma but

    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
     although
    -1.06
    可是
    -1.02
    昔
    -0.97
    但是
    -0.94
    食材
    -0.94
    結果
    -0.91
    あまり
    -0.90
     если
    -0.86
     телефона
    -0.85
    そして
    -0.85
    POSITIVE LOGITS
    要知道
    1.09
     setidaknya
    0.98
     profundas
    0.98
    潆
    0.95
     but
    0.95
    CloseHandle
    0.93
    nuss
    0.93
    近くに
    0.92
    有何
    0.92
    茕
    0.90
    Activations Density 0.132%

    No Known Activations