© 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. 22-GEMMASCOPE-RES-131K
    7. 34289
    Prev
    Next
    INDEX
    Explanations

    technical fields and services

    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_22/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
    あー
    -1.36
    tranh
    -1.34
    あぁ
    -1.23
    どういう
    -1.20
     another
    -1.20
    寝る
    -1.17
     inode
    -1.16
    centroid
    -1.15
     vestidos
    -1.13
     したい
    -1.13
    POSITIVE LOGITS
     system
    1.44
     is
    1.23
     performance
    1.23
     strategy
    1.13
     outcome
    1.13
     剑
    1.09
    <bos>
    1.09
     笔
    1.09
    を
    1.06
     design
    1.05
    Activations Density 0.215%

    No Known Activations