© 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. 1758
    Prev
    Next
    INDEX
    Explanations

    error reporting and handling

    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
    ⢪
    -2.75
    
    -2.34
     spearheaded
    -2.33
    Ᏹ
    -2.33
     Quando
    -2.20
    〮
    -2.16
     enseñ
    -2.13
    
    -2.11
     また
    -2.11
     própri
    -2.11
    POSITIVE LOGITS
    .
    3.17
    error
    2.80
    1
    2.78
    0
    2.72
    d
    2.67
    _
    2.56
    {
    2.27
    
    2.22
    );
    2.22
     Geräten
    2.20
    Activations Density 0.004%

    No Known Activations