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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75126
    Prev
    Next
    INDEX
    Explanations

    groups of people or entities

    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
     or
    -2.02
     it
    -1.92
     that
    -1.73
     to
    -1.71
     can
    -1.70
     time
    -1.48
     after
    -1.44
     will
    -1.37
     while
    -1.33
     is
    -1.32
    POSITIVE LOGITS
     Pristup
    2.06
     triko
    1.83
     people
    1.77
    沨
    1.74
     árbitro
    1.74
     those
    1.60
    Komentar
    1.59
     extrêmement
    1.57
    parfum
    1.57
     xadrez
    1.56
    Activations Density 0.209%

    No Known Activations