© 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. 34-GEMMASCOPE-RES-131K
    7. 23462
    Prev
    Next
    INDEX
    Explanations

    system commands and utilities

    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_34/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
     battles
    -0.81
    普通的
    -0.81
    fecture
    -0.76
    Battles
    -0.76
     лен
    -0.75
    一个月
    -0.75
    。』
    -0.74
     Grazing
    -0.73
     pintadas
    -0.73
     difícil
    -0.72
    POSITIVE LOGITS
    tool
    1.11
     utils
    1.05
    ctl
    1.04
    をしている
    0.93
     Hallmark
    0.90
    utils
    0.88
     utility
    0.86
    werkstatt
    0.86
    Į
    0.85
     Utility
    0.85
    Activations Density 0.170%

    No Known Activations