© 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. 115765
    Prev
    Next
    INDEX
    Explanations

    licensed code comments

    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
     Lode
    -0.84
    一條
    -0.75
     doros
    -0.71
     Freder
    -0.68
     föränd
    -0.66
    warf
    -0.66
     archived
    -0.65
    zionale
    -0.64
    lera
    -0.64
    が高
    -0.64
    POSITIVE LOGITS
    \|^{
    0.84
     Horton
    0.75
    gebied
    0.73
    Основ
    0.73
    ধ্য
    0.71
    司
    0.71
     司
    0.68
    дне
    0.68
    imbo
    0.67
     口コミ
    0.66
    Activations Density 0.056%

    No Known Activations