© 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. 45446
    Prev
    Next
    INDEX
    Explanations

    errors and Q statements

    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
     include
    -1.22
    include
    -1.11
     included
    -1.01
     includes
    -0.94
     Included
    -0.83
     Include
    -0.80
     includ
    -0.77
     inclusions
    -0.73
    包括
    -0.72
     вклю
    -0.69
    POSITIVE LOGITS
    ladora
    0.82
    isnan
    0.78
     flattered
    0.78
    <$
    0.75
     Schuster
    0.75
     podrob
    0.74
    เสีย
    0.73
    Evaluator
    0.73
    ेटा
    0.72
    ároz
    0.72
    Activations Density 0.113%

    No Known Activations