© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14024
    Prev
    Next
    INDEX
    Explanations

    European Myth

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

    process, induced, unfolding, pain, sharp, surface, smooth

    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_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
     I
    0.77
    0.64
     A
    0.62
     L
    0.57
     S
    0.54
     T
    0.54
     in
    0.54
     n
    0.52
     E
    0.52
     e
    0.51
    POSITIVE LOGITS
    WallArray
    0.45
    <end_of_turn>
    0.44
    ังหวัด
    0.44
    大多數
    0.44
    䄳
    0.44
    ᅱ
    0.44
    なわち
    0.43
    ร้อม
    0.43
    AutoStabilise
    0.43
    㯎
    0.43
    Activations Density 0.000%

    No Known Activations