© 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. 22-GEMMASCOPE-RES-131K
    4. 84505
    Prev
    Next
    INDEX
    Explanations

    closing brace and parenthesis

    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_22/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
    '},
    
    -0.94
     شد
    -0.85
    mya
    -0.84
    бования
    -0.84
    abancı
    -0.82
    summer
    -0.82
     évaluation
    -0.82
    大厅
    -0.81
     všech
    -0.81
     },
    
    -0.81
    POSITIVE LOGITS
    дцать
    0.90
     aviones
    0.85
     interface
    0.85
     Rasen
    0.84
     マウス
    0.83
     affatto
    0.82
    ereq
    0.80
    Waist
    0.79
     eleições
    0.79
    Dipl
    0.77
    Activations Density 0.002%

    No Known Activations