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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11514
    Prev
    Next
    INDEX
    Explanations

    Laravel template variables

    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_22/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
    ,"
    -2.14
    
    -1.97
    あります
    -1.93
    <bos>
    -1.90
    亊
    -1.77
    厹
    -1.76
    なる
    -1.75
     Unterschied
    -1.73
    :【
    -1.73
     riqueza
    -1.72
    POSITIVE LOGITS
    鲼
    1.95
    %")
    1.93
    ïdes
    1.89
    𐑂
    1.87
     hvilket
    1.81
    tabolism
    1.80
    %"),
    1.80
    😙
    1.79
    ))$_
    1.77
    銪
    1.74
    Activations Density 0.005%

    No Known Activations