© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22489
    Prev
    Next
    INDEX
    Explanations

    operators in code

    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
    ↵
    -1.89
     doesn
    -1.59
    led
    -1.38
     adhesivo
    -1.37
    只好
    -1.35
     but
    -1.34
    というのも
    -1.33
     be
    -1.32
    li
    -1.32
    should
    -1.30
    POSITIVE LOGITS
    彣
    1.58
     ТАК
    1.58
     fernández
    1.55
    gemeester
    1.55
    YOND
    1.55
    undang
    1.54
     BorderSide
    1.48
    誉
    1.48
    日语
    1.47
    Melon
    1.47
    Activations Density 0.048%

    No Known Activations