© 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. 11667
    Prev
    Next
    INDEX
    Explanations

    randomly selected from places/groups

    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
    {
    -2.38
    ↵↵
    -1.84
     There
    -1.60
     Apparently
    -1.60
     даже
    -1.59
     Even
    -1.57
     Perhaps
    -1.55
     However
    -1.55
    In
    -1.53
     While
    -1.50
    POSITIVE LOGITS
     uitgenodigd
    1.85
    驺
    1.84
    ౭
    1.82
     ſol
    1.77
    鼍
    1.65
     consulter
    1.64
    囖
    1.63
     sabid
    1.59
    НЫ
    1.59
    婠
    1.58
    Activations Density 0.061%

    No Known Activations