© 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. 70650
    Prev
    Next
    INDEX
    Explanations

    python 2.7 and python 3

    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
     was
    -2.14
    ’
    -2.14
     of
    -2.00
    DidLoad
    -1.73
     )
    -1.71
    ’.
    -1.67
    '!
    -1.67
    这一
    -1.65
    Menurutnya
    -1.63
    晢
    -1.59
    POSITIVE LOGITS
    鉭
    1.81
    魮
    1.66
    
    1.62
    摟
    1.61
    嘥
    1.60
    蒞
    1.57
     Sins
    1.55
    ită
    1.52
    してみた
    1.51
    
    1.51
    Activations Density 0.023%

    No Known Activations