© 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. 65538
    Prev
    Next
    INDEX
    Explanations

    tv show titles

    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
    For
    -2.06
     When
    -2.02
     Using
    -1.91
     This
    -1.88
     ;
    -1.87
    On
    -1.86
     =
    -1.85
    When
    -1.85
     Despite
    -1.84
     decreases
    -1.84
    POSITIVE LOGITS
    茈
    2.19
     seront
    1.92
    蟶
    1.84
     themſelves
    1.76
     唯美
    1.75
    畾
    1.70
     rompi
    1.69
     renaissance
    1.68
     帅气
    1.68
     seraient
    1.64
    Activations Density 0.033%

    No Known Activations