© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57888
    Prev
    Next
    INDEX
    Explanations

    gatekeeper, gatefold, Gates Foundation

    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
    andering
    -0.96
    tuigen
    -0.87
    nościo
    -0.83
     mohou
    -0.82
    ორ
    -0.81
    nasium
    -0.79
    yden
    -0.79
    arily
    -0.79
    sibility
    -0.79
    longed
    -0.78
    POSITIVE LOGITS
    keeper
    1.47
    keepers
    1.30
     Keeper
    1.16
    Keeper
    1.09
    Gate
    1.09
     keeper
    1.06
     keepers
    1.05
     Keepers
    1.01
     gate
    1.00
    hring
    0.95
    Activations Density 0.011%

    No Known Activations