© 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. 98371
    Prev
    Next
    INDEX
    Explanations

    code elements and configuration

    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
     its
    -0.95
     and
    -0.90
     has
    -0.89
     or
    -0.85
     their
    -0.84
    アリング
    -0.84
     equals
    -0.83
    MAPS
    -0.82
    MLElement
    -0.82
     helps
    -0.80
    POSITIVE LOGITS
    Už
    0.99
    neté
    0.98
     acontecimientos
    0.97
     TextAlign
    0.93
    
    0.91
    蹶
    0.91
    pertory
    0.90
    nae
    0.90
     dritte
    0.87
     AttributeSet
    0.87
    Activations Density 0.012%

    No Known Activations