© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63149
    Prev
    Next
    INDEX
    Explanations

    canvas stretcher

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on detailed product specification language—tokens describing canvas and frame materials, dimensions, and manufacturing qualities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    стма
    -0.78
    pytest
    -0.75
    クト
    -0.69
    팅
    -0.68
     Saltar
    -0.68
    BUCK
    -0.67
    Spire
    -0.66
     chronique
    -0.66
    OPENING
    -0.65
    columna
    -0.65
    POSITIVE LOGITS
     canvas
    1.66
     Canvas
    1.41
    canvas
    1.34
     stretcher
    1.29
    Canvas
    1.27
     gallery
    1.18
     canvases
    1.12
     stretched
    1.05
     Stretcher
    1.01
     canv
    0.93
    Activations Density 0.012%

    No Known Activations