© 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. 118937
    Prev
    Next
    INDEX
    Explanations

    St Andrew's origin

    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
    Still
    -2.55
    With
    -2.42
    i
    -2.39
    0
    -2.38
    What
    -2.25
    5
    -2.25
     longstanding
    -2.23
    Before
    -2.23
     Bereichen
    -2.22
    When
    -2.20
    POSITIVE LOGITS
    蕻
    2.73
    ㇼ
    2.66
    蹀
    2.58
    THERE
    2.48
    ഀ
    2.47
    
    2.47
    er
    2.42
    呖
    2.38
    
    2.34
     cartões
    2.33
    Activations Density 0.027%

    No Known Activations