© 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. 60659
    Prev
    Next
    INDEX
    Explanations

    Robbie Parker Oregon shooting

    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
     complicated
    -0.82
     people
    -0.77
     blijkt
    -0.77
     routes
    -0.73
     October
    -0.73
     complications
    -0.72
     capaces
    -0.71
    ddf
    -0.71
    ukar
    -0.69
     airport
    -0.68
    POSITIVE LOGITS
     Robb
    1.38
     Salvador
    1.06
    Salvador
    1.03
    Buffalo
    0.92
    Texas
    0.92
     Texans
    0.89
     salvador
    0.85
    Украина
    0.84
     texas
    0.83
    Divider
    0.81
    Activations Density 0.010%

    No Known Activations