© 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. 24030
    Prev
    Next
    INDEX
    Explanations

    criticism of, from, for

    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
     With
    -3.41
     Nearly
    -2.66
     For
    -2.53
     Having
    -2.48
     Of
    -2.47
     referenced
    -2.45
     ('
    -2.39
     Honestly
    -2.39
     Giving
    -2.39
     You
    -2.36
    POSITIVE LOGITS
    蘼
    2.98
    .
    2.56
    nothing
    2.52
    
    2.48
    
    2.47
    皤
    2.47
    蠖
    2.47
    those
    2.41
    izing
    2.38
    ほとん
    2.36
    Activations Density 0.002%

    No Known Activations