© 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. 1806
    Prev
    Next
    INDEX
    Explanations

    fantastic adjectives

    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
    ープン
    -2.98
    卺
    -2.84
    躂
    -2.83
    赑
    -2.81
     ſever
    -2.75
     trovo
    -2.73
    
    -2.73
     torner
    -2.67
     Projektu
    -2.66
    跸
    -2.63
    POSITIVE LOGITS
    .
    3.72
    {
    3.52
     Following
    2.75
    Thirty
    2.73
    ”
    2.72
    Following
    2.63
    ]
    2.61
    Another
    2.59
    Typically
    2.58
    Usually
    2.50
    Activations Density 0.007%

    No Known Activations