© 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. 47943
    Prev
    Next
    INDEX
    Explanations

    direction or purpose

    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
     almohada
    -1.67
     carcasa
    -1.60
     capucha
    -1.60
     représentants
    -1.56
     maceta
    -1.55
     pieles
    -1.51
     encaje
    -1.48
     manguera
    -1.45
     cristales
    -1.42
     tirantes
    -1.42
    POSITIVE LOGITS
     to
    8.19
     into
    2.56
     إلى
    2.20
     чтобы
    1.94
    to
    1.91
     để
    1.88
    DataTo
    1.87
     To
    1.73
     kepada
    1.67
     να
    1.66
    Activations Density 0.285%

    No Known Activations