© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90662
    Prev
    Next
    INDEX
    Explanations

    thats or whats introducing a statement

    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
     of
    -3.53
    <td>
    -3.03
     to
    -2.97
     and
    -2.89
     for
    -2.75
    i
    -2.72
     декабря
    -2.70
    ↑↑↑</
    -2.69
    鉝
    -2.64
    _{
    -2.56
    POSITIVE LOGITS
    
    3.05
    ᠌
    2.48
    ほうが
    2.47
     crossorigin
    2.44
     magnifique
    2.36
     sokak
    2.31
    EdgeInsets
    2.30
    甗
    2.28
    ↓
    2.28
     Nieuws
    2.28
    Activations Density 0.002%

    No Known Activations