© 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. 98692
    Prev
    Next
    INDEX
    Explanations

    code identifiers and properties

    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
    意识
    -0.91
     одного
    -0.87
    ↵↵
    -0.85
    intos
    -0.83
     enthalten
    -0.81
     lee
    -0.80
     verschiedener
    -0.80
     even
    -0.80
     zudem
    -0.79
     Es
    -0.78
    POSITIVE LOGITS
    好吃的
    1.05
     Scritto
    0.98
     Perché
    0.96
     émer
    0.96
    sistence
    0.93
    Nieuw
    0.93
    zerw
    0.92
    sisting
    0.90
     toucher
    0.89
    createNewFile
    0.88
    Activations Density 0.117%

    No Known Activations