© 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. 110754
    Prev
    Next
    INDEX
    Explanations

    throw exception error

    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
    uş
    -0.82
    淌
    -0.82
    :{
    -0.81
     fiction
    -0.81
    vno
    -0.77
    το
    -0.77
    쏜
    -0.76
    rinha
    -0.75
     rimu
    -0.75
     mute
    -0.75
    POSITIVE LOGITS
     Throw
    1.10
     throw
    1.08
     threw
    0.98
     into
    0.98
    throw
    0.97
     overboard
    0.96
    throwing
    0.93
     Throwing
    0.86
     throwing
    0.84
     werfen
    0.83
    Activations Density 0.004%

    No Known Activations