© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71790
    Prev
    Next
    INDEX
    Explanations

    numbers followed by million

    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
     it
    -1.90
     would
    -1.63
     In
    -1.59
    🤠
    -1.54
     as
    -1.46
     first
    -1.41
    )​
    -1.40
    ?”
    -1.39
     seemed
    -1.38
     betrekking
    -1.38
    POSITIVE LOGITS
    那我
    1.57
    7
    1.45
    =
    1.43
    銣
    1.39
    我这
    1.38
    不像
    1.33
     فعل
    1.32
    的模样
    1.31
     ۱۲
    1.30
    8
    1.30
    Activations Density 0.054%

    No Known Activations