© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13516
    Prev
    Next
    INDEX
    Explanations

    qualquer rechargeable Somali Alexandre

    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
    ’
    -3.58
    냑
    -3.06
    訁
    -3.00
    僦
    -2.95
    
    -2.94
     magnificent
    -2.88
    鲠
    -2.88
    튿
    -2.83
    料
    -2.83
    厹
    -2.80
    POSITIVE LOGITS
    0
    3.19
    what
    2.72
    1
    2.58
    7
    2.55
    -”
    2.50
    ти
    2.47
    )”
    2.44
    举动
    2.41
    4
    2.38
     ONLY
    2.34
    Activations Density 0.006%

    No Known Activations