© 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. 82935
    Prev
    Next
    INDEX
    Explanations

    library names and paths

    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
    tising
    -0.75
     brigade
    -0.74
     Luka
    -0.73
     melk
    -0.73
    böz
    -0.70
     lute
    -0.69
     Sentinel
    -0.69
     Brend
    -0.69
     Springsteen
    -0.69
     sama
    -0.69
    POSITIVE LOGITS
     liabilities
    4.69
     liability
    3.61
     Liabilities
    3.50
     Liability
    2.63
    Liability
    2.30
    liability
    2.28
    lib
    2.19
     lib
    2.16
     LIABILITY
    2.09
     assets
    1.90
    Activations Density 0.078%

    No Known Activations