© 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. 42739
    Prev
    Next
    INDEX
    Explanations

    develop skills and businesses

    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
     that
    -1.61
     for
    -1.36
    ?
    -1.33
    ↵
    -1.32
    or
    -1.30
     That
    -1.29
     or
    -1.28
    «
    -1.22
    cellent
    -1.22
    п
    -1.20
    POSITIVE LOGITS
     JULIO
    1.45
    妧
    1.44
     {
    
    1.36
     INFORMACIÓN
    1.35
     mientras
    1.35
    こういう
    1.34
    ዣ
    1.30
    CIUDAD
    1.30
     JOSÉ
    1.30
     enquanto
    1.29
    Activations Density 0.051%

    No Known Activations