© 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. 9997
    Prev
    Next
    INDEX
    Explanations

    Albert followed by last name

    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
    e
    -3.02
    ).
    -2.83
     These
    -2.61
    ↵↵
    -2.41
     
    -2.38
    id
    -2.28
     Ancak
    -2.23
    ',
    -2.19
    able
    -2.17
    a
    -2.17
    POSITIVE LOGITS
    鹇
    3.20
    鹟
    2.80
    ﹍﹍
    2.80
    衕
    2.78
    纜
    2.75
    Ꭳ
    2.56
    蓥
    2.52
     nevo
    2.52
    轎
    2.50
    Even
    2.48
    Activations Density 0.003%

    No Known Activations