© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93443
    Prev
    Next
    INDEX
    Explanations

    festivals and code snippets

    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
     escudo
    -0.79
     partes
    -0.76
     kanske
    -0.76
    noob
    -0.75
     recic
    -0.73
    Sulf
    -0.72
    気に
    -0.72
     Inglaterra
    -0.71
     }_{
    -0.71
    тив
    -0.70
    POSITIVE LOGITS
    赏
    0.80
     fifteenth
    0.78
     Festival
    0.77
     CPC
    0.75
    tegra
    0.72
    Gpu
    0.71
    став
    0.71
     legend
    0.70
     середине
    0.70
     display
    0.69
    Activations Density 0.010%

    No Known Activations