© 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. 28546
    Prev
    Next
    INDEX
    Explanations

    the CR citations

    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
    驅
    -0.94
     pname
    -0.83
    лец
    -0.81
     ہوا
    -0.80
    ンダー
    -0.79
     derni
    -0.79
    愜
    -0.76
    飛機
    -0.76
    爱你
    -0.74
     hetzelfde
    -0.74
    POSITIVE LOGITS
    把他
    0.84
    IZONT
    0.82
     synchronize
    0.82
    formatting
    0.82
     inclusion
    0.81
     pà
    0.80
     insiste
    0.79
    synchronize
    0.78
    тивность
    0.77
    ITEN
    0.76
    Activations Density 0.077%

    No Known Activations