© 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. 13257
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ۳
    -1.01
    anzeige
    -1.00
     plaît
    -0.99
    ֥
    -0.97
     ۴
    -0.96
     jsou
    -0.95
    ష్
    -0.95
     estar
    -0.95
     ۸
    -0.94
    』。
    -0.93
    POSITIVE LOGITS
     Fastest
    0.99
     atlantic
    0.93
     fian
    0.91
     téměř
    0.89
     합니다
    0.87
    过来了
    0.87
    віти
    0.86
    有何
    0.85
     formant
    0.84
     linden
    0.84
    Activations Density 0.000%

    No Known Activations