© 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. 7321
    Prev
    Next
    INDEX
    Explanations

    Q: followed by text

    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
    zog
    -0.96
     even
    -0.87
     most
    -0.81
    ặn
    -0.77
     Depending
    -0.77
     first
    -0.73
     grouped
    -0.73
     Several
    -0.72
    cu
    -0.72
     Despite
    -0.71
    POSITIVE LOGITS
     :=
    1.07
    ỡi
    1.01
    ckeye
    0.97
    üğü
    0.97
    ̶
    0.95
     unsettling
    0.94
    rfloor
    0.88
    rsquo
    0.88
    oulou
    0.88
    swald
    0.87
    Activations Density 0.001%

    No Known Activations