© 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. 34-GEMMASCOPE-RES-131K
    4. 103439
    Prev
    Next
    INDEX
    Explanations

    khadi khabir khatri

    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_34/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
    coroutines
    -0.75
     Intr
    -0.73
    -
    
    -0.71
    金牛
    -0.71
     amen
    -0.71
     vampires
    -0.71
    xffffff
    -0.71
    Extended
    -0.70
     inflater
    -0.70
    škai
    -0.70
    POSITIVE LOGITS
     setting
    0.84
     Kh
    0.82
     Setting
    0.79
     sottile
    0.75
     Erwart
    0.72
    rateful
    0.72
    kjø
    0.72
     albeit
    0.71
    kh
    0.70
    Kh
    0.70
    Activations Density 0.013%

    No Known Activations