© 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. 48384
    Prev
    Next
    INDEX
    Explanations

    amusement, reminding, convincing myself

    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
     we
    -2.23
    我们
    -1.77
    我們
    -1.70
     seiner
    -1.70
     themselves
    -1.68
    给我们
    -1.63
     его
    -1.59
    ıyoruz
    -1.55
     abbiamo
    -1.54
     нам
    -1.47
    POSITIVE LOGITS
     my
    6.44
     myself
    5.53
    myself
    3.34
     мои
    2.44
    我自己
    2.42
     خودم
    2.42
     Myself
    2.41
     моих
    2.36
    我的
    2.34
     моя
    2.28
    Activations Density 0.743%

    No Known Activations