© 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. 83423
    Prev
    Next
    INDEX
    Explanations

    questions starting with Q:

    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
     specified
    -0.86
     smaller
    -0.79
     Gesellschaft
    -0.77
     spent
    -0.76
    什么事
    -0.75
    诏
    -0.75
     może
    -0.75
     угол
    -0.75
     поч
    -0.74
    هی
    -0.74
    POSITIVE LOGITS
    ARIO
    0.81
    stimulated
    0.75
     {{{
    0.75
     ķ
    0.74
     midpoint
    0.73
    moud
    0.70
    Mateo
    0.70
    ಔ
    0.69
     }=\
    0.69
    rages
    0.69
    Activations Density 0.023%

    No Known Activations