© 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. 10-GEMMASCOPE-RES-131K
    4. 69096
    Prev
    Next
    INDEX
    Explanations

    fluid ounces of ingredients

    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_10/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
     their
    -1.71
     Putting
    -1.70
     There
    -1.69
     this
    -1.67
     sehr
    -1.59
     Before
    -1.59
     so
    -1.55
     Going
    -1.54
     Taking
    -1.53
     Getting
    -1.51
    POSITIVE LOGITS
     insanely
    1.40
    
    1.36
     escolh
    1.34
     specif
    1.29
     xxiii
    1.28
     kapture
    1.27
     ridiculously
    1.27
    
    1.27
     MICHAEL
    1.26
     Dinas
    1.24
    Activations Density 0.074%

    No Known Activations