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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98351
    Prev
    Next
    INDEX
    Explanations

    compound phrases

    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
     kwamba
    -0.84
     trafik
    -0.78
     Venedig
    -0.77
     ddr
    -0.77
     Golfo
    -0.75
     Santé
    -0.75
     kufanya
    -0.74
     cultivated
    -0.73
     серед
    -0.73
     zaragoza
    -0.71
    POSITIVE LOGITS
    instagram
    0.91
    Caratter
    0.81
    jwt
    0.81
    ouncements
    0.77
    ೭
    0.76
     jwt
    0.75
     registered
    0.73
     Zusammenarbeit
    0.72
     старости
    0.72
     vía
    0.71
    Activations Density 0.012%

    No Known Activations