© 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. 16-GEMMASCOPE-2-RES-16K
    7. 15250
    Prev
    Next
    INDEX
    Explanations

    respectively

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

    linking items in order

    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_16_width_16k_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
     enfer
    0.80
    t
    0.79
     Wyd
    0.77
     consiguió
    0.76
     considér
    0.75
     approu
    0.74
    <unused654>
    0.74
     wodurch
    0.72
    亚洲
    0.71
     jokingly
    0.71
    POSITIVE LOGITS
     respectively
    1.06
    respectively
    0.94
    ول
    0.88
    е
    0.80
     respectivamente
    0.73
    ни
    0.70
    ما
    0.70
    의
    0.70
     respective
    0.69
    도
    0.69
    Activations Density 0.096%

    No Known Activations