© 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. 98404
    Prev
    Next
    INDEX
    Explanations

    am or pm times

    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
    うわ
    -2.31
    おわりに
    -2.03
    久し
    -2.03
    もうすぐ
    -2.02
    えっ
    -2.02
    ところに
    -1.84
    急に
    -1.80
    Ꮉ
    -1.78
    いきなり
    -1.78
    いよいよ
    -1.77
    POSITIVE LOGITS
    0
    2.33
    u
    1.78
    a
    1.77
    m
    1.71
    但却
    1.70
    かが
    1.70
     when
    1.68
     другого
    1.66
    そういった
    1.66
    前は
    1.63
    Activations Density 0.003%

    No Known Activations