© 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. 12398
    Prev
    Next
    INDEX
    Explanations

    Dimension followed by letter

    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
     landes
    -1.41
    ຣ
    -1.40
    อ่าน
    -1.38
    ského
    -1.38
    larınız
    -1.32
     Mereka
    -1.30
    ANTAGES
    -1.30
    Além
    -1.29
     asiático
    -1.27
    ların
    -1.27
    POSITIVE LOGITS
     erforderlich
    1.54
     ApiService
    1.39
     wtedy
    1.30
     unless
    1.27
     MatDialog
    1.25
    
    1.24
     декора
    1.22
     alltid
    1.21
    エリー
    1.21
     nossas
    1.20
    Activations Density 0.001%

    No Known Activations