Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 309
    Prev
    Next
    INDEX
    Explanations

    roman numerals

    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
     your
    -2.28
    s
    -2.08
    1
    -1.97
    t
    -1.82
    g
    -1.70
    D
    -1.69
    0
    -1.67
    3
    -1.62
    m
    -1.59
    p
    -1.55
    POSITIVE LOGITS
    %"),
    1.65
    %");
    1.59
    癀
    1.56
    ]));
    
    1.53
    ")),
    1.52
     Polskiego
    1.52
     CreateTagHelper
    1.51
    )))
    
    1.48
    ":[{
    1.47
     Patience
    1.46
    Activations Density 0.103%

    No Known Activations