© 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. 80783
    Prev
    Next
    INDEX
    Explanations

    looks like, a little, a lot

    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
    跗
    -2.13
     bén
    -2.08
    なのですが
    -2.08
    訁
    -2.06
     râ
    -2.06
     rése
    -2.06
    ֢
    -2.02
    釔
    -1.98
    炱
    -1.97
    
    -1.95
    POSITIVE LOGITS
    “
    2.17
     -
    2.13
    -
    1.99
     like
    1.98
    $
    1.98
    '
    1.94
    ↵↵
    1.79
     similar
    1.76
    on
    1.71
    ;
    1.70
    Activations Density 0.014%

    No Known Activations