© 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. 86690
    Prev
    Next
    INDEX
    Explanations

    copyright and reserved

    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
    翃
    -2.47
    矬
    -2.30
    geſ
    -2.02
     satisfe
    -2.00
    蓠
    -1.95
     выбрать
    -1.94
    ╽
    -1.93
    ⌵
    -1.92
     når
    -1.91
    titure
    -1.88
    POSITIVE LOGITS
    2
    3.03
    8
    2.77
    4
    2.45
    Perhaps
    2.31
    7
    2.27
    While
    2.25
    6
    2.25
    的大
    2.23
     Although
    2.23
    9
    2.19
    Activations Density 0.036%

    No Known Activations