© 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. 102543
    Prev
    Next
    INDEX
    Explanations

    private access modifiers

    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
     exteriores
    -1.02
    wissenschaften
    -0.91
    sans
    -0.90
     involucrados
    -0.86
     externo
    -0.86
    IRM
    -0.86
     možno
    -0.85
     separados
    -0.85
     corporativa
    -0.85
    ktar
    -0.84
    POSITIVE LOGITS
    private
    4.03
     private
    3.75
     a
    3.17
     privaten
    2.16
     Private
    2.14
    fileprivate
    2.03
     privately
    2.02
    私
    1.97
    Private
    1.95
    PRIVATE
    1.95
    Activations Density 0.049%

    No Known Activations