© 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. 72851
    Prev
    Next
    INDEX
    Explanations

    much-needed or deserved things

    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
    轶
    -1.89
     でも
    -1.78
    しますが
    -1.77
    扩大
    -1.72
     exposiciones
    -1.70
    瀟
    -1.68
    熒
    -1.66
     f
    -1.62
     helicópter
    -1.59
     generaciones
    -1.56
    POSITIVE LOGITS
     图解
    1.91
     素描
    1.80
     hout
    1.79
     groen
    1.78
    歺
    1.76
     kangoo
    1.75
     汽车
    1.73
     champignons
    1.73
     strategis
    1.71
     baden
    1.70
    Activations Density 0.005%

    No Known Activations