© 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. 34622
    Prev
    Next
    INDEX
    Explanations

    Green Lantern and associated creators

    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
    檚
    -0.79
     Alpine
    -0.77
    pecia
    -0.77
     logits
    -0.75
    マジック
    -0.75
     aspirin
    -0.73
     Falco
    -0.73
     alpine
    -0.72
    Alpine
    -0.71
     этом
    -0.70
    POSITIVE LOGITS
     Lantern
    1.59
     lantern
    1.47
     Corps
    1.31
     constructs
    1.26
     Green
    1.22
     construct
    1.17
     lanterns
    1.12
     Constructs
    1.11
    Green
    1.10
    construct
    1.08
    Activations Density 0.011%

    No Known Activations