© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129015
    Prev
    Next
    INDEX
    Explanations

    yahoo

    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
     But
    -2.73
    眥
    -2.59
     Fünf
    -2.55
    鲠
    -2.53
     The
    -2.48
     แต่
    -2.47
    .”
    -2.42
    
    -2.42
    felpa
    -2.39
     และ
    -2.28
    POSITIVE LOGITS
    硨
    2.89
    ↵↵
    2.27
    .
    2.25
    ции
    2.05
    }
    1.99
     LECT
    1.95
    抬手
    1.94
    鋨
    1.91
    `
    1.89
     projets
    1.88
    Activations Density 0.006%

    No Known Activations