© 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. 119317
    Prev
    Next
    INDEX
    Explanations

    programming interfaces

    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
    adır
    -0.79
    busters
    -0.78
    訊息
    -0.76
    髮
    -0.71
    handlers
    -0.71
    towany
    -0.71
     principi
    -0.71
    やかに
    -0.70
    wertes
    -0.70
     referring
    -0.68
    POSITIVE LOGITS
     interface
    1.39
    interface
    1.13
    接口
    1.09
     interfaces
    1.01
    interfaces
    0.91
     Interface
    0.90
     hither
    0.88
    iesti
    0.85
    ilber
    0.85
    жным
    0.85
    Activations Density 0.045%

    No Known Activations