© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79303
    Prev
    Next
    INDEX
    Explanations

    dw prefix

    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
    Negative Logits
     recogni
    -0.85
    ERTE
    -0.82
     Recognizing
    -0.80
     horsemen
    -0.80
    єте
    -0.79
     attainments
    -0.79
     Obtaining
    -0.79
     dogmatic
    -0.78
     consummation
    -0.78
     condiments
    -0.78
    POSITIVE LOGITS
     dw
    1.26
     Dw
    1.16
    dw
    1.07
     DW
    1.03
    ight
    1.02
    Dw
    0.87
    IGHT
    0.77
     dwell
    0.76
    رفع
    0.76
    Ordered
    0.70
    Activations Density 0.024%

    No Known Activations