© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1495
    Prev
    Next
    INDEX
    Explanations

    programmatic return values

    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
     formó
    -0.80
    дове
    -0.79
    ubri
    -0.79
     Пло
    -0.77
    >>();
    -0.77
    логических
    -0.77
     llevó
    -0.77
     étro
    -0.76
    сени
    -0.75
    hasNext
    -0.74
    POSITIVE LOGITS
     exit
    1.42
    Exit
    1.30
     Exit
    1.19
     error
    1.17
     EXIT
    1.15
    exit
    1.07
    EXIT
    1.07
     exiting
    1.01
     failure
    1.01
     success
    1.00
    Activations Density 0.003%

    No Known Activations