© 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. 34-GEMMASCOPE-RES-131K
    7. 50059
    Prev
    Next
    INDEX
    Explanations

    if and only if

    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_34/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
    ഔ
    -0.88
    kswagen
    -0.84
    ҉
    -0.82
     ROH
    -0.80
    ඟ
    -0.80
     ThreadPool
    -0.79
    usakan
    -0.79
     जाएगा
    -0.78
    хов
    -0.77
     voci
    -0.77
    POSITIVE LOGITS
     only
    1.71
     ONLY
    1.55
    only
    1.54
     Only
    1.37
    ONLY
    1.34
    Only
    1.30
     тільки
    1.19
     numai
    1.17
     только
    1.17
     tylko
    1.16
    Activations Density 0.012%

    No Known Activations