© 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. 57009
    Prev
    Next
    INDEX
    Explanations

    image effects and styling

    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
    zav
    -0.79
    anwal
    -0.77
    íu
    -0.76
    찔
    -0.74
     forested
    -0.71
    楠
    -0.71
    chanan
    -0.70
    тія
    -0.69
     Callum
    -0.68
    ümüş
    -0.68
    POSITIVE LOGITS
     dodge
    1.05
     highlights
    1.00
     soft
    0.97
     softer
    0.92
     Hard
    0.91
    highlights
    0.91
     embossed
    0.90
     Soft
    0.89
    Soft
    0.87
     reflections
    0.87
    Activations Density 0.024%

    No Known Activations