© 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. 80618
    Prev
    Next
    INDEX
    Explanations

    thank u or you

    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
    }
    -1.71
     ikke
    -1.71
    ↵↵
    -1.68
    Tentang
    -1.64
     our
    -1.62
    
    -1.62
    皛
    -1.61
    勦
    -1.55
     kartą
    -1.54
    Więcej
    -1.53
    POSITIVE LOGITS
    囫
    1.68
                                   
    1.67
     of
    1.66
    捋
    1.66
    vantaged
    1.62
                        
    1.59
    by
    1.59
    匆
    1.57
     ché
    1.53
    其妙
    1.52
    Activations Density 0.040%

    No Known Activations