© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127918
    Prev
    Next
    INDEX
    Explanations

    anniversary or birth announcements

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

    ordering events before others

    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_31_width_262k_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
     Bake
    0.51
    昕
    0.49
    한국
    0.47
     Barley
    0.47
     By
    0.47
     Buh
    0.47
    Hors
    0.46
    Formatting
    0.46
    By
    0.45
    Bring
    0.44
    POSITIVE LOGITS
     حرام
    0.47
     annivers
    0.46
    にとって
    0.44
    arantad
    0.42
     करती
    0.41
    iduciary
    0.41
    elerinin
    0.41
     た
    0.40
    眠
    0.40
    流れ
    0.39
    Activations Density 0.003%

    No Known Activations