© 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. 10-GEMMASCOPE-RES-131K
    7. 120098
    Prev
    Next
    INDEX
    Explanations

    Mage::getModel

    np_acts-logits-general · gemini-2.5-flash-lite

    method calls or function invocations in code, particularly those using dot notation or the `::` operator.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    _
    -2.14
    When
    -1.95
     
    -1.76
     if
    -1.74
    For
    -1.73
    (
    -1.70
    If
    -1.65
     When
    -1.60
    ↵↵
    -1.59
    Not
    -1.57
    POSITIVE LOGITS
    
    1.90
     administratif
    1.62
    𓆏
    1.59
    #%%
    1.59
     frança
    1.57
    雠
    1.56
    bricas
    1.55
    塒
    1.55
     ボア
    1.55
     ferrovia
    1.55
    Activations Density 0.001%

    No Known Activations