© 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. 37921
    Prev
    Next
    INDEX
    Explanations

    variable initialization

    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
     SYSTEM
    -1.66
     system
    -1.59
    System
    -1.59
    system
    -1.52
     System
    -1.48
     système
    -1.37
     система
    -1.31
    SYSTEM
    -1.30
     sistema
    -1.30
     سیستم
    -1.30
    POSITIVE LOGITS
     Integer
    2.11
    Integer
    1.75
     java
    1.55
     Character
    1.28
    java
    1.27
    Character
    1.18
     Double
    1.16
     new
    1.09
     (
    1.07
     javafx
    1.03
    Activations Density 0.018%

    No Known Activations