© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60855
    Prev
    Next
    INDEX
    Explanations

    load and restore configurations

    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
     Weitere
    -0.84
     créer
    -0.84
    Encode
    -0.83
     Daarnaast
    -0.82
     beobachtet
    -0.82
     Aufgrund
    -0.81
    crire
    -0.79
     черен
    -0.79
     CREATE
    -0.78
     Generate
    -0.77
    POSITIVE LOGITS
     load
    2.00
    读取
    1.68
    load
    1.68
     retrieve
    1.66
     retrieved
    1.55
     retrieving
    1.52
     loads
    1.52
     retrieval
    1.52
     read
    1.48
     restore
    1.47
    Activations Density 0.055%

    No Known Activations