© 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. 10-GEMMASCOPE-RES-131K
    4. 3606
    Prev
    Next
    INDEX
    Explanations

    scanning objects or spaces

    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_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
    ?!”
    -1.94
     ภาพถ่าย
    -1.70
    イヤル
    -1.70
    ים
    -1.68
    denken
    -1.67
     Hacer
    -1.65
     While
    -1.65
    gün
    -1.64
    тами
    -1.63
     Although
    -1.62
    POSITIVE LOGITS
    ?
    2.61
     тысячи
    2.25
     самая
    2.05
    ."
    1.99
     первая
    1.91
     origins
    1.83
     duża
    1.75
    ।
    1.72
    Scan
    1.72
    in
    1.70
    Activations Density 0.026%

    No Known Activations