© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 74017
    Prev
    Next
    INDEX
    Explanations

    multi-lingual or specific word endings

    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
    gruntled
    -0.97
    зербай
    -0.95
     mercies
    -0.94
    фотография
    -0.93
     éx
    -0.92
     DANS
    -0.91
     VOUS
    -0.90
    esség
    -0.87
     donc
    -0.87
     harmed
    -0.87
    POSITIVE LOGITS
     or
    0.85
     one
    0.85
     aldı
    0.82
     подоб
    0.81
     taşı
    0.76
    urium
    0.76
    seys
    0.73
    ệu
    0.73
     only
    0.72
     after
    0.72
    Activations Density 0.003%

    No Known Activations