© 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. 90313
    Prev
    Next
    INDEX
    Explanations

    American locations and technology

    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
    龶
    -1.57
    吅
    -1.51
    ड़ा
    -1.42
    龵
    -1.38
     juſt
    -1.38
    
    -1.36
    niest
    -1.30
    畕
    -1.25
    ciled
    -1.23
    givings
    -1.23
    POSITIVE LOGITS
    ਖ਼
    1.73
     will
    1.65
    度
    1.60
     weirdly
    1.54
     that
    1.48
    力
    1.47
     these
    1.46
    ਫ਼
    1.43
     this
    1.37
     espirituales
    1.37
    Activations Density 0.572%

    No Known Activations