© 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. 876
    Prev
    Next
    INDEX
    Explanations

    relegated, banished, or confined

    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
     of
    -2.11
     achieved
    -1.57
     deference
    -1.55
    ússia
    -1.52
    }
    -1.48
     帳
    -1.46
    킵
    -1.43
    edoria
    -1.42
    rittura
    -1.41
    šenie
    -1.41
    POSITIVE LOGITS
    ↵
    1.66
     menyebutkan
    1.58
     ۹
    1.55
     gants
    1.52
     there
    1.52
     bross
    1.50
     betek
    1.48
    ࿆
    1.48
     tylko
    1.48
     mengaku
    1.48
    Activations Density 0.013%

    No Known Activations