© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4359
    Prev
    Next
    INDEX
    Explanations

    numbers and web addresses

    np_acts-logits-general · gemini-2.5-flash-lite

    special characters or list formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prisoners
    0.42
    宻
    0.41
     refrigerators
    0.39
     অন্য
    0.39
    畈
    0.38
     refreshments
    0.37
     እና
    0.37
     해서
    0.37
    䔧
    0.37
     ኤ
    0.36
    POSITIVE LOGITS
    fi
    0.39
     mar
    0.38
    <unused60>
    0.37
     lucro
    0.37
    ko
    0.37
     permitan
    0.37
    zon
    0.37
     nevo
    0.37
    aron
    0.37
    opus
    0.37
    Activations Density 0.008%

    No Known Activations