© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 16032
    Prev
    Next
    INDEX
    Explanations

    words of contrast and concession

    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
    authorised
    -0.85
     venter
    -0.81
     Tiss
    -0.80
    нительно
    -0.79
     rester
    -0.79
    霹
    -0.79
    ταν
    -0.78
     borg
    -0.78
     vermo
    -0.77
    因为它
    -0.77
    POSITIVE LOGITS
     although
    2.30
     though
    1.81
     aunque
    1.72
    Although
    1.70
    although
    1.66
     Nevertheless
    1.66
     however
    1.59
     хотя
    1.57
     البته
    1.52
     Although
    1.51
    Activations Density 0.035%

    No Known Activations