© 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. 116821
    Prev
    Next
    INDEX
    Explanations

    boolean values and related logic

    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
    暇
    -0.89
    >>;
    -0.83
     Elsa
    -0.82
    zná
    -0.81
    出版社
    -0.80
     POT
    -0.79
    нка
    -0.79
    ガ
    -0.78
    ėl
    -0.78
    érature
    -0.77
    POSITIVE LOGITS
     False
    0.92
    False
    0.78
     regarding
    0.77
     Friedens
    0.73
     Anywhere
    0.70
     enquiries
    0.70
    Regarding
    0.69
     Hampden
    0.69
     鸭
    0.69
     alot
    0.69
    Activations Density 0.019%

    No Known Activations