© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109782
    Prev
    Next
    INDEX
    Explanations

    PL/SQL blocks and keywords

    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
     chết
    -0.77
    厨师
    -0.73
    sizePolicy
    -0.73
     kra
    -0.73
     lite
    -0.71
     Waller
    -0.71
    Seu
    -0.71
    nten
    -0.71
     honte
    -0.69
    Fernando
    -0.69
    POSITIVE LOGITS
     PL
    0.92
    pl
    0.88
    PL
    0.82
     PLS
    0.81
     EXIT
    0.81
    PKG
    0.81
     package
    0.76
    院
    0.76
    pkg
    0.74
    BODY
    0.74
    Activations Density 0.113%

    No Known Activations