© 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. 86657
    Prev
    Next
    INDEX
    Explanations

    lay ministry and organizations

    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
    {
    -1.79
    蕯
    -1.69
     even
    -1.69
     any
    -1.67
     also
    -1.66
     because
    -1.62
     with
    -1.60
     Their
    -1.56
     nine
    -1.55
     Because
    -1.52
    POSITIVE LOGITS
    \_\_
    1.62
    stwie
    1.58
    טרה
    1.55
    how
    1.55
     \_
    1.51
    ogue
    1.50
    between
    1.46
    through
    1.45
     fiasco
    1.41
    ፨
    1.41
    Activations Density 0.205%

    No Known Activations