© 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. 22-GEMMASCOPE-RES-131K
    7. 26681
    Prev
    Next
    INDEX
    Explanations

    both contrasting pairs

    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_22/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
    faring
    -0.98
    banken
    -0.96
    caling
    -0.90
    lexikon
    -0.89
    runner
    -0.89
    cess
    -0.88
    fielder
    -0.88
     軽量
    -0.88
    不得不说
    -0.86
    了一些
    -0.86
    POSITIVE LOGITS
     both
    1.47
     for
    1.05
     både
    1.02
    both
    1.01
     пър
    1.00
    ltä
    0.96
     pierws
    0.95
     Both
    0.93
     první
    0.93
     Euch
    0.93
    Activations Density 0.107%

    No Known Activations