© 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. 103873
    Prev
    Next
    INDEX
    Explanations

    Bioshock

    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
    metti
    -0.84
    ärme
    -0.82
    pageCount
    -0.77
     fragmentation
    -0.77
     alignItems
    -0.76
    nodeId
    -0.74
    Capp
    -0.73
    Filmography
    -0.73
    /></
    -0.73
    iomanip
    -0.72
    POSITIVE LOGITS
     Bios
    1.09
    Bios
    1.02
     bios
    0.98
     plasmids
    0.94
     plasmid
    0.92
     Comstock
    0.91
     Bio
    0.88
     Columbia
    0.86
     Booker
    0.85
    Bio
    0.84
    Activations Density 0.015%

    No Known Activations