© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 973
    Prev
    Next
    INDEX
    Explanations

    giving up everything

    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
    bero
    -0.83
     satisfacción
    -0.81
     ansvar
    -0.77
     Receipts
    -0.76
    korb
    -0.76
     thôi
    -0.76
     trail
    -0.75
    нутрен
    -0.74
    omás
    -0.73
     ラーメン
    -0.73
    POSITIVE LOGITS
     everything
    1.68
    everything
    1.47
    Everything
    1.30
     to
    1.23
     Everything
    1.10
     EVERYTHING
    1.04
     tudo
    1.02
    เพื่อ
    1.02
     wszystko
    1.00
     entire
    0.99
    Activations Density 0.020%

    No Known Activations