© 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. 10-GEMMASCOPE-RES-131K
    4. 11870
    Prev
    Next
    INDEX
    Explanations

    using a method or tool

    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
    :
    
    -1.80
    .'
    -1.80
     was
    -1.79
    ㉨
    -1.73
     '
    -1.70
    💯
    -1.67
    他是
    -1.66
     inz
    -1.66
    蹋
    -1.66
    ,'
    -1.65
    POSITIVE LOGITS
     unangemess
    2.16
    a
    2.02
     beschränkt
    2.00
     ponieważ
    1.95
    5
    1.91
    谂
    1.85
    the
    1.84
    美国的
    1.83
     várias
    1.79
     wiederhol
    1.77
    Activations Density 0.070%

    No Known Activations