© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50102
    Prev
    Next
    INDEX
    Explanations

    light interference and quantum states

    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
    
    -0.88
     profitability
    -0.75
    tix
    -0.74
    clearfix
    -0.74
     brisk
    -0.72
    uwen
    -0.71
    ricas
    -0.71
    混合
    -0.71
    phanumeric
    -0.69
    ocity
    -0.69
    POSITIVE LOGITS
     suspendu
    1.01
     Hanford
    1.01
     VIR
    0.88
     Recycled
    0.87
    IFO
    0.85
     Virgo
    0.83
     Violin
    0.83
     Seismic
    0.82
    ligo
    0.81
     interfer
    0.81
    Activations Density 0.018%

    No Known Activations