© 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. 75159
    Prev
    Next
    INDEX
    Explanations

    programming imports, questions, celebrities

    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
     السياس
    -1.30
     capucha
    -1.28
    ଵ
    -1.24
     الشم
    -1.24
    
    -1.23
    逦
    -1.23
    ⌗
    -1.20
    謚
    -1.19
    ۤ
    -1.19
    ("
    -1.18
    POSITIVE LOGITS
    Karakter
    1.71
    Kamu
    1.57
    Doktor
    1.47
    Fakta
    1.45
    Seni
    1.44
     Wartawan
    1.41
    Gön
    1.41
    Jawab
    1.38
    Instrumented
    1.38
    Paket
    1.34
    Activations Density 0.070%

    No Known Activations