© 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. 23455
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, java 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_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
     thuis
    -0.67
     Freeman
    -0.66
     修改
    -0.66
     genotype
    -0.66
     можете
    -0.65
    льтра
    -0.65
    ßer
    -0.64
    atikan
    -0.64
    灰色
    -0.63
     Тю
    -0.63
    POSITIVE LOGITS
    你了
    0.71
    lenir
    0.68
    AddNew
    0.68
     Presentations
    0.67
    ":{
    0.66
    HAD
    0.66
    yam
    0.66
    six
    0.66
    retched
    0.64
     discur
    0.64
    Activations Density 0.081%

    No Known Activations