© 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. 22-GEMMASCOPE-RES-131K
    7. 84397
    Prev
    Next
    INDEX
    Explanations

    programming code structures

    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_22/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
     not
    -2.06
     all
    -2.00
     most
    -1.87
     their
    -1.77
     this
    -1.73
     many
    -1.67
     only
    -1.65
     first
    -1.60
     in
    -1.58
     both
    -1.58
    POSITIVE LOGITS
     Эти
    1.74
     パッド
    1.68
     figliu
    1.56
     schuhe
    1.45
     Dinas
    1.44
     weihnachten
    1.43
     richiede
    1.42
     لهذه
    1.38
    ᛬
    1.38
    
    1.37
    Activations Density 0.005%

    No Known Activations