© 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. 34-GEMMASCOPE-RES-131K
    7. 80765
    Prev
    Next
    INDEX
    Explanations

    constructor and destructor declarations

    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_34/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
     PÅ
    -0.94
    侗
    -0.93
     alternative
    -0.89
     millon
    -0.88
    cyjnych
    -0.88
     particular
    -0.86
    taker
    -0.86
     different
    -0.85
    phrodite
    -0.85
     ryzen
    -0.83
    POSITIVE LOGITS
     después
    1.01
     will
    0.95
    QtGui
    0.90
     setelah
    0.88
     =
    0.85
     żad
    0.83
     cuyo
    0.83
    Aunque
    0.82
    之处
    0.81
     nothing
    0.80
    Activations Density 0.006%

    No Known Activations