© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 97912
    Prev
    Next
    INDEX
    Explanations

    selective [noun]

    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
    </strong>
    -1.61
    エレ
    -1.05
    .
    -1.04
     xác
    -1.00
    bof
    -0.98
    ↵
    -0.97
     ingestion
    -0.97
    allen
    -0.96
    ért
    -0.95
     factored
    -0.95
    POSITIVE LOGITS
     Selecting
    1.73
     selezion
    1.47
     选择
    1.42
    selecting
    1.42
     parmi
    1.40
     selects
    1.40
    Selecting
    1.38
     Selection
    1.36
     Select
    1.34
     Selections
    1.34
    Activations Density 0.063%

    No Known Activations