© 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. 10-GEMMASCOPE-RES-131K
    7. 42372
    Prev
    Next
    INDEX
    Explanations

    topics and questions

    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_10/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
    atellite
    -1.53
     örgü
    -1.52
    前期
    -1.49
    
    -1.48
    艿
    -1.47
    exemple
    -1.47
     kemarin
    -1.44
     [''],
    -1.44
     ideales
    -1.42
    荩
    -1.42
    POSITIVE LOGITS
     then
    1.76
     ability
    1.61
     effort
    1.59
     it
    1.55
     relações
    1.47
     situações
    1.45
     circumstances
    1.45
     he
    1.45
     said
    1.44
    on
    1.42
    Activations Density 0.003%

    No Known Activations