© 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. 62402
    Prev
    Next
    INDEX
    Explanations

    graphics texture coordinates and color

    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
     мне
    -0.77
     Haag
    -0.71
    Leaky
    -0.71
    燴
    -0.69
    neval
    -0.69
    Rus
    -0.68
     lecz
    -0.68
    vorous
    -0.66
    明治
    -0.65
    ynb
    -0.65
    POSITIVE LOGITS
     colors
    1.29
     colours
    0.96
    colors
    0.93
     Colors
    0.92
    glTexCoord
    0.91
    Norma
    0.90
     colores
    0.89
     tangents
    0.86
     норма
    0.86
     color
    0.86
    Activations Density 0.011%

    No Known Activations