© 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. 86995
    Prev
    Next
    INDEX
    Explanations

    every aspect or cross-cutting

    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
    Some
    -1.79
     after
    -1.71
     for
    -1.63
     Currently
    -1.63
     will
    -1.57
     on
    -1.55
     While
    -1.52
     in
    -1.47
     Since
    -1.46
     out
    -1.45
    POSITIVE LOGITS
     cinquième
    1.66
    閖
    1.52
     quatrième
    1.48
     Affects
    1.46
    
    1.44
     playera
    1.43
    扨
    1.43
     ivel
    1.43
     ſen
    1.42
     både
    1.41
    Activations Density 0.077%

    No Known Activations