© 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. 10-GEMMASCOPE-RES-131K
    4. 61143
    Prev
    Next
    INDEX
    Explanations

    component tags

    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
    تصویر
    -1.99
     new
    -1.80
    مرحله
    -1.80
    توضی
    -1.80
     debía
    -1.75
     powied
    -1.68
    افز
    -1.62
     podía
    -1.61
    Reak
    -1.59
     confirmó
    -1.54
    POSITIVE LOGITS
    电机
    1.51
     Algunas
    1.50
     along
    1.49
    
    1.49
     vgl
    1.48
     Organización
    1.45
     abſ
    1.45
    some
    1.43
    particularly
    1.41
    enosis
    1.39
    Activations Density 0.055%

    No Known Activations