© 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. 22-GEMMASCOPE-RES-131K
    7. 67754
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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_22/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
     controver
    -1.01
    Amicalement
    -1.01
     your
    -0.98
     krim
    -0.96
     caricatura
    -0.95
    tous
    -0.94
     cabina
    -0.94
     Buka
    -0.94
     suporta
    -0.93
     intest
    -0.93
    POSITIVE LOGITS
    ↵
    1.22
     T
    0.95
    ;
    0.91
    }
    0.89
     excepto
    0.87
    );
    0.84
     LGBTQ
    0.84
     metrów
    0.83
     D
    0.83
    E
    0.82
    Activations Density 0.002%

    No Known Activations