© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12639
    Prev
    Next
    INDEX
    Explanations

    mathematical and code syntax

    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
     logiciels
    -1.09
     چیه
    -1.02
     etap
    -1.00
     assinatura
    -0.99
    cheque
    -0.98
     Quando
    -0.95
    nesty
    -0.94
    ฀
    -0.94
    lng
    -0.93
    在意
    -0.91
    POSITIVE LOGITS
     using
    1.27
    結果は
    1.13
     elettrico
    1.05
     does
    1.02
    Lokasi
    1.00
    How
    1.00
    Ekster
    1.00
     spesielt
    1.00
     pistas
    0.98
     or
    0.97
    Activations Density 0.223%

    No Known Activations