© 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. 22-GEMMASCOPE-RES-131K
    7. 79676
    Prev
    Next
    INDEX
    Explanations

    locations and people

    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
     something
    -1.05
    ꨄ
    -1.02
    bertas
    -1.00
     using
    -0.94
     sorella
    -0.93
    hasPermission
    -0.93
    指標
    -0.92
    　＊
    -0.91
    mindedness
    -0.91
    샅
    -0.90
    POSITIVE LOGITS
     who
    2.13
     whom
    1.45
    who
    1.30
    whom
    1.03
     quienes
    0.96
    whose
    0.95
    acaktır
    0.95
    硏
    0.88
     whose
    0.87
    tamia
    0.85
    Activations Density 0.090%

    No Known Activations