© 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. 90761
    Prev
    Next
    INDEX
    Explanations

    Dates and times

    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
    håll
    -0.83
     موا
    -0.76
    oper
    -0.76
    습
    -0.76
    parent
    -0.74
    фф
    -0.73
    hani
    -0.73
    рыя
    -0.72
    Helper
    -0.71
    helper
    -0.71
    POSITIVE LOGITS
    cenzo
    1.00
     wydaj
    0.83
     mít
    0.83
    дила
    0.82
     공식
    0.80
    ocino
    0.80
    obal
    0.79
     naturlig
    0.79
    Kdo
    0.79
    . 
    0.78
    Activations Density 0.001%

    No Known Activations