© 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. 22-GEMMASCOPE-RES-131K
    7. 34879
    Prev
    Next
    INDEX
    Explanations

    keywords or identifiers within quotes

    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
    derry
    -1.00
     recommande
    -0.99
     pelbagai
    -0.96
     bulan
    -0.88
     tulang
    -0.88
     kaca
    -0.87
    nade
    -0.86
     fitur
    -0.86
     člove
    -0.86
     embalagem
    -0.85
    POSITIVE LOGITS
     elevada
    0.94
    ObjectModel
    0.93
     to
    0.90
     of
    0.90
     solicitado
    0.90
     Він
    0.89
    \_
    0.89
    ではある
    0.89
    ]{
    0.88
    の人は
    0.87
    Activations Density 0.011%

    No Known Activations