© 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. 47493
    Prev
    Next
    INDEX
    Explanations

    day of

    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
    {
    -2.19
     Füßen
    -2.02
     dunklen
    -1.91
    ፱
    -1.84
     contain
    -1.80
    ような
    -1.78
    ᯾
    -1.74
    loween
    -1.74
     ewigen
    -1.73
     yalnızca
    -1.72
    POSITIVE LOGITS
    l
    2.03
     sidan
    1.88
    跟
    1.86
    也是
    1.80
     なし
    1.80
    我们
    1.80
    焢
    1.77
    r
    1.74
    学的
    1.74
    al
    1.74
    Activations Density 0.009%

    No Known Activations