© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68604
    Prev
    Next
    INDEX
    Explanations

    academic course and program descriptions

    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_22/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
    Even
    -1.66
     even
    -1.41
    Despite
    -1.38
    During
    -1.34
    Like
    -1.30
    广西
    -1.28
    Two
    -1.27
    Several
    -1.26
     laku
    -1.24
     intricacies
    -1.23
    POSITIVE LOGITS
     všech
    1.38
     kolem
    1.30
     focuses
    1.30
    primarily
    1.28
     čtyř
    1.27
    があるので
    1.25
     veřej
    1.24
     soooo
    1.23
     valoración
    1.23
    earlier
    1.22
    Activations Density 0.001%

    No Known Activations