© 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. 89800
    Prev
    Next
    INDEX
    Explanations

    hereby granted permission

    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
    weza
    -0.75
    polski
    -0.73
    paginate
    -0.73
    onion
    -0.73
    Watt
    -0.73
    ofile
    -0.72
     stadig
    -0.71
    ᚦ
    -0.71
     Hussain
    -0.71
     söyle
    -0.70
    POSITIVE LOGITS
     Stati
    0.71
    アリング
    0.68
     (:
    0.67
    𝓓
    0.67
     General
    0.66
    ags
    0.66
    EAC
    0.66
     ({
    0.66
    针对
    0.66
     MCS
    0.66
    Activations Density 0.030%

    No Known Activations