© 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. 103031
    Prev
    Next
    INDEX
    Explanations

    app settings and configuration

    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
     desej
    -0.75
     latter
    -0.73
     ranging
    -0.73
    ⓘ
    -0.73
     Instead
    -0.71
    を求
    -0.71
     originalen
    -0.69
    形成
    -0.69
     instead
    -0.68
    jenkins
    -0.68
    POSITIVE LOGITS
     getApp
    0.94
     gjør
    0.94
    Ghi
    0.87
    驳
    0.86
    getApp
    0.86
    künfte
    0.84
    ending
    0.84
    ആ
    0.82
     älskar
    0.82
    upy
    0.82
    Activations Density 0.028%

    No Known Activations