© 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. 110497
    Prev
    Next
    INDEX
    Explanations

    let's hope

    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
     to
    -1.79
    してみてください
    -1.44
    二日
    -1.41
     даже
    -1.39
     detach
    -1.38
     You
    -1.38
     लिए
    -1.34
    ⼼
    -1.31
    ্প
    -1.30
     intricacies
    -1.28
    POSITIVE LOGITS
    <td>
    1.63
    
    1.54
     algodão
    1.54
    釹
    1.53
    {$\
    1.49
     geändert
    1.44
     tecido
    1.41
     principaux
    1.41
    妧
    1.41
     somewhat
    1.38
    Activations Density 0.007%

    No Known Activations