© 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. 115491
    Prev
    Next
    INDEX
    Explanations

    boolean assignments in code structure

    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
     NSCoder
    -0.97
     MotionEvent
    -0.96
    があり
    -0.92
     finit
    -0.90
    FirstResponder
    -0.90
    詒
    -0.89
     pitié
    -0.89
     görüş
    -0.88
     intptr
    -0.88
    csak
    -0.87
    POSITIVE LOGITS
     true
    1.98
     false
    1.34
     True
    1.28
    true
    1.27
     yes
    1.26
     TRUE
    1.16
     untrue
    1.02
     cierto
    0.96
    false
    0.86
     tru
    0.86
    Activations Density 0.022%

    No Known Activations