© 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. 36674
    Prev
    Next
    INDEX
    Explanations

    such as

    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
     both
    -1.21
     some
    -1.16
     most
    -1.11
     because
    -1.06
    Both
    -1.05
     give
    -1.01
     versatile
    -1.00
     strong
    -0.99
     high
    -0.98
     gives
    -0.98
    POSITIVE LOGITS
    νη
    1.04
     ayur
    1.01
     angiel
    0.98
    
    0.96
    も含
    0.95
    邛
    0.95
     여러
    0.94
    iae
    0.93
     ameryka
    0.93
     ľudí
    0.92
    Activations Density 0.064%

    No Known Activations