© 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. 110506
    Prev
    Next
    INDEX
    Explanations

    code structure 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
     JsonConvert
    -1.14
    JOptionPane
    -0.89
     вже
    -0.84
     malfunctions
    -0.79
    nemer
    -0.79
    Futures
    -0.78
    warnings
    -0.77
    BIC
    -0.76
     deque
    -0.75
    insets
    -0.75
    POSITIVE LOGITS
     javafx
    0.99
     like
    0.88
     our
    0.86
    org
    0.85
     quite
    0.83
     org
    0.82
     just
    0.81
     androidx
    0.77
     Everybody
    0.75
     hemos
    0.75
    Activations Density 0.081%

    No Known Activations