© 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. 57489
    Prev
    Next
    INDEX
    Explanations

    data types and programming constructs

    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
     That
    -1.68
     стране
    -1.63
    嗳
    -1.55
    蘑菇
    -1.53
     определение
    -1.51
    APPLAUSE
    -1.49
    ereço
    -1.45
    )</
    -1.44
    ië
    -1.41
    寅
    -1.41
    POSITIVE LOGITS
    1
    1.80
    橚
    1.73
    this
    1.70
     this
    1.62
     vixion
    1.52
    鼱
    1.52
    蹌
    1.49
     existentes
    1.45
    es
    1.43
    它的
    1.41
    Activations Density 0.004%

    No Known Activations