© 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. 10-GEMMASCOPE-RES-131K
    7. 12409
    Prev
    Next
    INDEX
    Explanations

    filter circuits 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_10/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
    ྥ
    -1.92
    锲
    -1.66
     (“
    -1.49
    
    -1.48
    あっという
    -1.42
    ate
    -1.41
    うーん
    -1.41
    ’
    -1.41
    何时
    -1.40
    迨
    -1.40
    POSITIVE LOGITS
    '
    1.79
    e
    1.68
     säl
    1.41
    kadang
    1.37
    吴
    1.35
    getItemId
    1.34
    芭
    1.34
     not
    1.34
    ي
    1.33
    ]
    1.30
    Activations Density 0.017%

    No Known Activations