© 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. 3663
    Prev
    Next
    INDEX
    Explanations

    Beer's law, light, Lambert, Phong

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

    programming and technical file format elements, particularly in material and lighting specifications.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
    Nj
    -0.73
     מכ
    -0.72
    刻
    -0.69
    olars
    -0.69
    umumkan
    -0.69
     tratamientos
    -0.68
     accedere
    -0.66
     blanco
    -0.66
    eratops
    -0.66
    ホワイト
    -0.65
    POSITIVE LOGITS
     Lambert
    1.86
    Lambert
    1.63
     LAM
    1.16
     Lam
    1.15
    mbert
    1.13
     Beer
    1.11
    Beer
    1.06
     Phong
    1.02
     la
    0.98
    Phong
    0.94
    Activations Density 0.081%

    No Known Activations