© 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. 131063
    Prev
    Next
    INDEX
    Explanations

    programming language syntax

    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
    ,
    -0.97
    休み
    -0.85
    なければならない
    -0.83
     will
    -0.81
     mutter
    -0.77
     on
    -0.77
    จีน
    -0.77
     gud
    -0.76
     flushing
    -0.75
     early
    -0.75
    POSITIVE LOGITS
     estekak
    1.08
     pietra
    1.03
     gewähr
    1.02
     basiert
    1.02
    "]();
    1.02
     beruht
    0.98
    tismo
    0.96
    aconda
    0.95
     egenskaper
    0.94
    の作成
    0.94
    Activations Density 0.003%

    No Known Activations