© 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. 54192
    Prev
    Next
    INDEX
    Explanations

    years and dates

    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
    PACS
    -1.02
     bobina
    -1.02
    hosa
    -0.99
     który
    -0.98
     professione
    -0.96
    клопе
    -0.96
     Naciones
    -0.94
     který
    -0.93
     抠
    -0.92
    cão
    -0.91
    POSITIVE LOGITS
     also
    1.63
     stesso
    1.08
    另一
    1.02
     another
    0.96
     ayrıca
    0.94
     також
    0.91
     immediately
    0.88
     separate
    0.87
     également
    0.85
    also
    0.85
    Activations Density 0.018%

    No Known Activations