© 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. 81340
    Prev
    Next
    INDEX
    Explanations

    view / views

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

    The neuron chiefly activates on occurrences of the term “view” (especially “View” in code), i.e. references to view‐related classes or functions in source.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Nerd
    -0.87
     umożliwia
    -0.85
    快樂
    -0.84
     Netanyahu
    -0.83
     tortillas
    -0.83
    関連項目
    -0.83
     парка
    -0.81
    ࿔
    -0.81
    Marianne
    -0.81
    зера
    -0.79
    POSITIVE LOGITS
     хочется
    0.83
    DOUBLE
    0.81
    Garden
    0.79
    grey
    0.78
                        
    0.75
    ᠶ
    0.75
     getroffen
    0.74
     Garden
    0.74
    Substituting
    0.74
    ="@+
    0.73
    Activations Density 0.015%

    No Known Activations