© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 20939
    Prev
    Next
    INDEX
    Explanations

    Gibson, West Ham, deserts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä
    0.97
    and
    0.92
    %
    0.82
    3
    0.79
    FS
    0.78
    ?
    0.77
    ig
    0.76
     deutsche
    0.75
    IN
    0.75
    4
    0.74
    POSITIVE LOGITS
     on
    0.89
     unwa
    0.79
    ન
    0.75
    ご理解
    0.73
     for
    0.71
     }}$
    0.71
     оно
    0.70
    。\
    0.70
     niż
    0.70
    кати
    0.69
    Activations Density 0.000%

    No Known Activations