© 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. 93762
    Prev
    Next
    INDEX
    Explanations

    texture filtering and wrapping

    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
     Trial
    -0.80
    ディー
    -0.79
    Trained
    -0.78
    それでは
    -0.76
     секун
    -0.74
     injected
    -0.73
    ParallelGroup
    -0.73
    Приятного
    -0.72
     Whyte
    -0.72
     olmak
    -0.70
    POSITIVE LOGITS
    glTex
    1.26
     wrap
    1.06
    wrapping
    1.05
     WRAP
    1.02
     FILTER
    1.02
     wrapping
    1.01
     Wrap
    1.01
     Filtering
    1.00
     filtering
    0.98
     Wrapping
    0.98
    Activations Density 0.009%

    No Known Activations