© 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. 59208
    Prev
    Next
    INDEX
    Explanations

    draws

    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
    carry
    -0.80
    música
    -0.76
     الصحة
    -0.75
    enteric
    -0.75
     trabalhos
    -0.75
    carteles
    -0.74
     tâche
    -0.73
    aprend
    -0.73
     inició
    -0.73
    ßerdem
    -0.73
    POSITIVE LOGITS
     draw
    2.16
     drawing
    1.77
     draws
    1.75
    draw
    1.74
     drew
    1.68
     drawn
    1.64
     Draw
    1.55
    Draw
    1.51
    drawing
    1.38
     Draws
    1.32
    Activations Density 0.008%

    No Known Activations