© 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. 34-GEMMASCOPE-RES-131K
    4. 90987
    Prev
    Next
    INDEX
    Explanations

    date and version

    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_34/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
    OutOf
    -0.81
     Winfield
    -0.76
     LEAVE
    -0.75
    awsze
    -0.74
    omb
    -0.74
     exhibitions
    -0.74
    Gain
    -0.73
     Zar
    -0.72
     Inclusion
    -0.71
    leave
    -0.71
    POSITIVE LOGITS
     suspicious
    0.70
    Gerd
    0.67
     bénéfices
    0.66
     prudent
    0.65
     dormitory
    0.64
    +/**
    0.64
     Pio
    0.63
    墜
    0.63
    Bunch
    0.63
    curated
    0.62
    Activations Density 0.029%

    No Known Activations