© 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. 7167
    Prev
    Next
    INDEX
    Explanations

    large selection variety

    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
    幾個
    -0.88
    Zitat
    -0.83
    ωμα
    -0.80
    idae
    -0.78
    CharStream
    -0.77
     both
    -0.77
     áreas
    -0.77
     Several
    -0.76
    ícula
    -0.75
     all
    -0.75
    POSITIVE LOGITS
     selection
    4.84
    selection
    3.59
    Selection
    3.47
     variety
    3.42
     selections
    3.30
     Selection
    3.28
     SELECTION
    3.11
     range
    2.92
     assortment
    2.81
     Auswahl
    2.75
    Activations Density 0.063%

    No Known Activations