© 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. 34-GEMMASCOPE-RES-131K
    7. 98511
    Prev
    Next
    INDEX
    Explanations

    exception handling and class definitions

    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_34/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
    擽
    -1.25
    
    -1.16
     participer
    -1.16
     GOtt
    -1.16
     comportamento
    -1.12
     传统
    -1.11
     折り
    -1.11
     Anſ
    -1.08
    扨
    -1.08
    adors
    -1.06
    POSITIVE LOGITS
     (
    1.67
    :
    1.54
     as
    1.50
     except
    1.39
     Exception
    1.34
     ALL
    1.25
     []:
    1.20
     September
    1.16
     February
    1.16
     or
    1.15
    Activations Density 0.002%

    No Known Activations