© 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. 80730
    Prev
    Next
    INDEX
    Explanations

    specific items or concepts

    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
     and
    -2.44
     but
    -2.06
    These
    -1.76
    Our
    -1.72
    Another
    -1.70
    ࿚
    -1.70
    Every
    -1.66
    Several
    -1.64
    ándor
    -1.63
     groundbreaking
    -1.62
    POSITIVE LOGITS
    ING
    1.80
    va
    1.78
      
    1.78
    _
    1.63
                           
    1.63
     into
    1.59
    vi
    1.59
     its
    1.57
                                   
    1.55
    кі
    1.55
    Activations Density 0.156%

    No Known Activations