© 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. 34-GEMMASCOPE-RES-131K
    7. 64092
    Prev
    Next
    INDEX
    Explanations

    programming exceptions thrown

    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
     安卓
    -0.90
    pezif
    -0.88
    VISED
    -0.88
    frances
    -0.88
     Bagi
    -0.88
    Suspended
    -0.84
    Proceedings
    -0.82
     AspNetCore
    -0.81
     quelli
    -0.81
    んですが
    -0.80
    POSITIVE LOGITS
     thrown
    1.81
     when
    1.62
     throw
    1.44
     if
    1.42
    throw
    1.38
     throws
    1.34
     threw
    1.12
     если
    1.11
     upon
    1.11
     will
    1.11
    Activations Density 0.009%

    No Known Activations