© 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. 61058
    Prev
    Next
    INDEX
    Explanations

    problems and specific names

    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
     sprüche
    -3.30
    礽
    -3.25
    焄
    -3.16
    摃
    -3.16
    潆
    -3.03
     ſch
    -2.97
    跸
    -2.91
    桄
    -2.89
     anhänger
    -2.88
     起毛
    -2.86
    POSITIVE LOGITS
    .
    2.91
    ↵↵
    2.91
     Around
    2.80
     \
    2.69
     Meanwhile
    2.64
    &
    2.53
    {
    2.53
     Until
    2.48
     
    2.45
    _{
    2.44
    Activations Density 0.006%

    No Known Activations