© 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. 106117
    Prev
    Next
    INDEX
    Explanations

    length and wavelength scales

    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
     tellement
    -0.79
     faciliter
    -0.79
    Resposta
    -0.79
    Wouldn
    -0.77
    vrier
    -0.77
     Dinas
    -0.76
    scheduled
    -0.75
     póster
    -0.74
    Doesn
    -0.74
    픔
    -0.74
    POSITIVE LOGITS
     wavelength
    2.17
     wavelengths
    1.67
    wavelength
    1.55
     length
    1.50
     Wavelength
    1.36
     size
    1.34
     characteristic
    1.28
     coherence
    1.27
     lengths
    1.19
    Wavelength
    1.16
    Activations Density 0.055%

    No Known Activations