© 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. 118563
    Prev
    Next
    INDEX
    Explanations

    made changes

    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
     devons
    -0.87
    geschäft
    -0.85
    DeleteMapping
    -0.83
    ımı
    -0.81
    Sizes
    -0.81
    ]=>
    -0.80
    ムラ
    -0.79
    멜
    -0.79
    ganya
    -0.78
    itania
    -0.78
    POSITIVE LOGITS
     changes
    5.88
    changes
    4.28
     Changes
    3.84
    Changes
    3.81
     change
    3.69
     modifications
    3.38
     изменения
    3.20
     CHANGES
    3.19
     alterations
    3.13
     perubahan
    3.08
    Activations Density 0.219%

    No Known Activations